This study provides a detailed examination of Natural Language Processing (NLP) for the complexscript of Nepali. We analyze available data resources today and discuss relevant points includingcharacter encoding, advanced tokenization methods and morphological complexity. This allows us tocontrast Nepal’s unique language and technology ecosystem with Hindi and Thai in terms of NLPadvancements. Quantitative assessment of existing tools and resources is offered by this investigationwhich highlights immediate weaknesses as well as areas that need more effort. Various ethicalconcerns are addressed here while potential topics for future research as e-governance, healthcare oreducation with a focus on new domain-specific applications, and cross-lingual transfer learning aresuggested. The objective of this attempt is to enhance understanding of natural language processing(NLP) in Nepali language and beyond aimed at developing NLP technologies that are more efficient,inclusive, culturally appropriate across diverse linguistic communities.

In a densely populated country like Bangladesh, universities grapple with the challenge of efficiently addressing myriad queries from a large student body, leading to a heightened workload for university stakeholders. To tackle these challenges, we introduce PixieGPT, a tailor-made Generative Pre-Trained Transformer for Bangladeshi universities. PixieGPT significantly mitigates workload by adeptly handling common university-related queries, thereby enhancing user experience. The hierarchical structure plays a crucial role in managing diverse queries from thousands of students about the university system. The solution introduces a modular hierarchical knowledge base (KB) with simpler complexities, addressing the intricacies of efficiently managing large volumes of queries. PixieGPT is designed in a modular way so that the solution is also adaptable for the implementation of other universities worldwide based on the requirements of a particular administrative system. The modular nature facilitates easy adaptation with minor changes based on specific university requirements, ensuring a seamless integration process. This paper delves into the intricacies of PixieGPT's design, emphasizing its pivotal role in mitigating workload challenges for university stakeholders in Bangladesh. The incorporation of BERT for Natural Language Understanding(NLU) and GPT models for Natural Language Generation(NLG) enhances PixieGPT's capabilities, contributing to the scalability and efficiency of the system. The presented use case underscores the practical benefits of PixieGPT, positioning it as a promising solution for universities globally with similar operational frameworks.

Pre-trained Language Models (PTLM) have remarkable and successful performance in solving lots of NLP tasks nowadays. And previous researchers have created many SOTA models and these models are included in many long surveys(Qiu et al., 2020). So, we would like to conduct a simple and short survey on this topic to help researchers understand the sketch of PTLM more quickly and comprehensively. In this short survey, we would provide a simple but comprehensive review of techniques, benchmarks, and methodologies in PTLM. And we would also introduce the applications evaluation of PTLM in this simple survey.

In dementia, particularly Alzheimer's Disease (AD), communication challenges are evident, especially in vocabulary and pragmatic aspects. Affected individuals often use vague, non-specific words, and their speech lacks informative nouns and verbs, leading to imprecise communication. However, aspects like sentence structure, phonology, and articulation are believed to remain intact until later stages, though this view is debated in the research community. The rise of Large Language Models (LLMs) has made significant strides in various domains, including sentiment analysis and question-answering. These advancements have been applied to dementia research, with studies using LLMs to analyze textual data. Some research incorporates pauses in text to enhance performance, while others utilize transfer learning techniques. However, limited datasets for dementia detection pose challenges in training LLMs. Our research presents a novel approach to measuring the impact of in-text encoding strategies by embedding special characters within the text to enhance model performance and incorporating sequences and summaries of their frequency. Our best model achieves 0.88 and 0.86 in f1-score and accuracy, respectively, whereas the baseline has 0.42 and 0.56 in f1-score and accuracy.

English based datasets are commonly available from Kaggle, GitHub, or recently published papers. Although benchmark tests with English datasets are sufficient to show off the performances of new models and methods, still a researcher need to train and validate the models on Korean based datasets to produce a technology or product, suitable for Korean processing. This paper introduces 15 popular Korean based NLP datasets with summarized details such as volume, license, repositories, and other research results inspired by the datasets. Also, I provide high-resolution instructions with sample or statistics of datasets. The main characteristics of datasets are presented on a single table to provide a rapid summarization of datasets for researchers.

The internet has changed the way people perceived fiction to a new level. For instance, online forums have given people the opportunity to write without revealing their real identities. Especially in the Saudi context, online users were using these forums to write web novels that reflect their culture, lives, concerns, hopes and dreams. In this paper, we describe a dataset that was collected from one of the online forums that was used for sharing web novels among its readers. The collected dataset contains 1,267 novels between 2003-2015. This data set is available to the research community to analyze to gain a better understanding of the social, economical, and behavioral mindset that was manifested in the community in that decade.

Only languages with abundant resources are given the opportunity to build speech recognition systems, whereas low resource languages are disregarded. This project attempts to create a system that can normally convert speech to text in the Myanmar (Burmese) language, a language part of low resource languages. The Burmese language is extremely intricate and is made up of vowels, consonants, tones, and stress. There are 10 numbers, 12 vowels, and 33 letters in the Myanmar alphabet. Deep learning allows for the evolution of numerous algorithms while eradicating ignorance and even low-resource languages may be turned into speech-to-text systems with a small quantity of data. The procedures required to construct a successful speech recognition system that can assist both the corporate sector and society will be covered in this project, including data collecting, preprocessing, modeling, prototyping, assessment, and ultimately deployment.

Chinese texts often feature a substantial volume of normative content, and their analysis has increasingly become a focal point in recent semantic analysis endeavors. Enhancing the effectiveness of text classification and clustering is pivotal in unveiling the intricate semantics within extensive textual data. Empirical research within the realm of computational social science has underscored the need for improved explanatory power when it comes to general text clustering methods applied to normative texts. This study introduces an innovative hierarchical clustering method that incorporates part-of-speech (POS) features and pioneers a novel semantic network model. It achieves this by amalgamating a POS-based feature weight calculation method with hierarchical clustering techniques. To assess its efficacy, the method is rigorously evaluated across three diverse text datasets, encompassing normative reports, news articles, and social media content. The experimental results unequivocally demonstrate the superior performance of the POS-HC method, surpassing the traditional TF and TF-IDF feature extraction methods in terms of clustering accuracy, and surpassing some existing clustering methods. Furthermore, its classification effectiveness exhibits notable advantages, particularly in the semantic classification of normative texts.

Child sexual abuse inflicts lifelong devastating consequences for victims and is an ongoing social concern. In most countries, child sexual abuse material (CSAM) distribution is illegal. As a result, there are many research papers in the literature which proposed technologies to detect and investigate CSAM. In this survey, a comprehensive search of the peer-reviewed journal and conference paper databases (including preprints) is conducted to identify high-quality literature. We use the PRISMA methodology to refine our search space to 2,761 papers published by Springer, Elsevier, IEEE and ACM. After iterative reviews of title, abstract and full text for relevance to our topics, 43 papers are included for full review. Our paper provides a comprehensive synthesis of the tasks of the current research and how the papers use techniques and datasets to solve their tasks and evaluate their models. To the best of our knowledge, we are the first to focus exclusively on online CSAM detection and prevention with no geographic boundaries, and the first survey to review papers published after 2018. It can be used by researchers to identify gaps in knowledge and relevant publicly available datasets that may be useful for their research.

Smartphones are prone to SMS phishing due to the rapid growth in the availability of smart mobile technologies driven by Internet connections. Also, detecting phishing SMS is a challenging task due to the unstructured nature of SMS text data with non-linear complex correlations. In this concern, considering the recent advancements in the domain of cybersecurity, we have proposed a hybrid deep learning framework that extracts robust features from SMS texts followed by an automatic detection of Phishing SMS. Due to combining the potential capability of individual models into one hybrid framework, it has outperformed various other individual machine learning and deep learning models. The proposed Phishing Detection framework is an effective hybrid combination of pretrained transformer model, MPNet (Masked and Permuted Language Modeling), with supervised ConvNets (CNN) and Bi-directional Gated Recurrent Units (GRU). It is intended to successfully detect unstructured short phishing text messages that contain complex patterns.

With the rapid development of science and technology, many new concepts and terms appear, especially in English. Other languages try to express these concepts with words from their own vocabulary. In the specific case of Arabic, there are many ways to find a counterpart for a particular new concept, such as using an existing word to denote the new concept, derivation, and blending. When these methods fail, the new concepts are simply phonetically transliterated. This has the disadvantage that most of the transliterated terms do not conform to the rules of the Arabic language and lead to a distortion of the language. Some modern linguists call for using the generation strategy to translate the new terms into Arabic by using the unused Arabic roots. Therefore, it is necessary to provide a resource that contains all Arabic roots with a categorization of what is used, what is available for use, and what is rejected according to the phonetic system. This work provides a comprehensive lexicon that contains all possible Arabic triliteral roots, determines the status of each root in terms of usage and acceptability, and provides a mechanism for giving preference to roots when there is more than one root that indicates the desired meaning.

With the rapid development of science and technology, many new concepts and terms appear, especially in English. Other languages try to express these concepts with words from their own vocabulary. In the specific case of Arabic, there are many ways to find a counterpart for a particular new concept, such as using an existing word to denote the new concept, derivation, and blending. When these methods fail, the new concepts are simply phonetically transliterated. This has the disadvantage that most of the transliterated terms do not conform to the rules of the Arabic language and lead to a distortion of the language. Some modern linguists call for using the generation strategy to translate the new terms into Arabic by using the unused Arabic roots. Therefore, it is necessary to provide a resource that contains all Arabic roots with a categorization of what is used, what is available for use, and what is rejected according to the phonetic system. This work provides a comprehensive lexicon that contains all possible Arabic triliteral roots, determines the status of each root in terms of usage and acceptability, and provides a mechanism for giving preference to roots when there is more than one root that indicates the desired meaning.

In the digital age, social media platforms have become a significant source of both information and misinformation, presenting challenges and opportunities for threat intelligence. Natural Language Processing (NLP) has emerged as a powerful tool for extracting actionable insights from the vast amounts of unstructured text generated on these platforms. This paper explores the application of NLP techniques to enhance social media threat intelligence, focusing on methodologies for detecting and analyzing threats such as disinformation, cyberbullying, and extremist content. We examine various NLP approaches, including sentiment analysis, topic modeling, and entity recognition, and their effectiveness in identifying and mitigating potential risks. The paper also addresses the challenges associated with processing social media data, such as dealing with slang, context, and multilingual content. By leveraging NLP, organizations can improve their ability to monitor and respond to emerging threats in real-time, ultimately enhancing their overall security posture. The findings suggest that while NLP offers significant benefits, it must be complemented by human expertise and ethical considerations to ensure accurate and responsible threat assessment.

Historic expeditions are events that are flavored by exploratory, scientific, military or geographic characteristics. Such events are often documented in literature, journey notes or personal diaries. A typical historic expedition involves multiple site visits and their descriptions contain spatiotemporal and attributive contexts. Expeditions involve movements in space that can be represented by triplet features (location, time and description). However, such features are implicit and innate parts of textual documents. Extracting the geospatial information from these documents requires understanding the contextualized entities in the text. To this end, we developed a semi-automated framework that has multiple Information Retrieval and Natural Language Processing components to extract the spatiotemporal information from a two-volumes historic expedition gazetteer. Our framework has three basic components, namely, the Text Preprocessor, the Gazetteer Processing Machine and the JAPE (Java Annotation Pattern Engine) Transducer. We used the Brazilian Ornithological Gazetteer as an experimental dataset and extracted the spatial and temporal entities from entries that refer to three expeditioners’ site visits and mapped the trajectory of each expedition using the extracted information. Finally, one of the mapped trajectories was manually compared with a historical reference map of that expedition to assess the reliability of our framework. The reference map was manually prepared in previous research work by others.

Recurrent Neural Networks (RNNs) have significantly advanced the field of machine learning by enabling the effective processing of sequential data. This paper provides a comprehensive review of RNNs and their applications, highlighting advancements in architectures such as Long Short-Term Memory (LSTM) networks, Gated Recurrent Units (GRUs), Bidirectional LSTM (BiLSTM), and stacked LSTM. The study examines the application of RNNs in different domains, including natural language processing (NLP), speech recognition, financial time series forecasting, bioinformatics, autonomous vehicles, and anomaly detection. Additionally, the study discusses recent innovations, such as the integration of attention mechanisms and the development of hybrid models that combine RNNs with convolutional neural networks (CNNs) and transformer architectures. This review aims to provide machine learning researchers and practitioners with a comprehensive overview of the current state and future directions of RNN research.

This study applies several natural language processing techniques for characterizing social groups by analyzing published text in social media. The resulting computed values are proposed as features for modeling social groups and measure distances or similarities among them, along further data that could help understanding group behavior according to language usage. In this study, we have analyzed the messages published on Twitter regarding patriotism by the main political parties in Spain. The results show that lexical resources and topic modelling algorithms are useful to model different groups and serve as comparison tools to better understand the topics these groups are talking about.

We describe a dataset that contains job description published on a popular online website in the information and technology sector. As the website focus mainly on United Kingdom based jobs, the data have a specific focus on this country. It contains 11.501 job vacancies and 13 related meta data information. The dataset is suitable for HR analysis using machine learning techniques such as natural language processing and neural networks.

Recent advancements in neural machine translation (NMT) offer promising potential for generating cross-language clinical natural language processing (NLP) resources. There is a pressing need to be able to foster the development of clinical NLP tools that extract key clinical entities in a comparable way for a multitude of medical application scenarios, hindered by lack of multilingual annotated data. This study explores the efficacy of using NMT and annotation projection techniques with expert in the loop validation to develop named entity recognition (NER) systems for an under resourced target language (Catalan) by leveraging Spanish clinical corpora annotated by domain experts. We employed a state-of-the-art NMT system to translate three clinical case corpora. The translated annotations were then projected onto the target language texts and subsequently validated and corrected by clinical domain experts. The efficacy of the resulting NER systems was evaluated against manually annotated test sets in the target language. Our findings indicate that this approach not only facilitates the generation of high-quality training data for the target language (Catalan) but also demonstrates the potential to extend this methodology to other languages, thereby enhancing multilingual clinical NLP resource development. The generated corpora and components are publicly accessible, providing potentially a valuable resource for further research and application in multilingual clinical settings: https://zenodo.org/doi/10.5281/zenodo.13133124.

Dementia, primarily caused by neurodegenerative diseases like Alzheimer’s disease (AD), affects millions worldwide, making detection and monitoring crucial. To enable these tasks, we propose encoding in-text pauses and filler words (i.e., “uh” and “um”) in text-based language models, and thoroughly evaluate their effect in performance. Additionally, we suggest using contrastive learning to improve performance in a multi-task framework. Our results demonstrated the effectiveness of our approaches in enhancing the model’s performance, achieving 87% accuracy and an 86% F1-score. Compared to the state-of-the-art, our approach has similar performance despite having significantly fewer parameters. This highlights the importance of pause and filler word encoding on the detection of dementia.

In the application domain, accurate word sense identification is crucial for improving the performance of machine translation, information retrieval and end-to-end communication tasks. However, word polysemy is a major obstacle to accurate semantic identification. Therefore, word semantic disambiguation has always been one of the key challenges in natural language processing and has attracted the attention of a large number of researchers. This research proposes an innovative disambiguation algorithm based on the large-scale Bert model and the Polly encoder framework, and introduces WordNet as a benchmark for word semantic. By exploiting the ability of the pre-trained model to extract and learn semantic information, and using a specially designed forward propagation algorithm and loss function to fine-tune the large-scale Bert model, the model has high Accuracy and robustness. In this research, several experiments were conducted on the Semcor 3.0 semantic dataset. The experimental results show that the model proposed in this research shows excellent performance on the Semcor test set, with an Accuracy of 86.1% and an F1 score of 0.847, which is a significant improvement over the traditional model.

Backgrounds: The field of Artificial Intelligence (AI) has seen a major shift in recent years due to the development of new Machine Learning (ML) models such as Generative Pre-trained Transformer (GPT) and AI which are progressively becoming part our everyday lives. GPT has achieved previously unheard-of levels of accuracy in most computerized language processing tasks and their chat-based variations. Aim: The aim of this study was to investigate the problem-solving abilities of ChatGPT using two sets of verbal insight problems, with a known performance level established by a sample of human participants. Material and Methods: A total of 30 problems labelled as “practice problems” and “transfer problems”, as listed by Ansburg and Dominowski (2000), were administered to ChatGPT. The answers provided by ChatGPT received a score of "0" for each problem answered incorrectly and a score of "1" for each correct response, as per the correct solution specified in Ansburg and Dominowski's (2000) study. The highest score that could be attributed to both the practice and transfer problems was 15 out of 15. In order to compare ChatGPT performance to the performance to that of human subjects, the solution rate for each problem (based on a sample of 20 subjects) was used, as indicated by Ansburg and Dominowski (2000). Results: The study highlighted that ChatGPT can be trained in out-of-the-box thinking and demonstrated potential in solving verbal insight problems. The global performance of ChatGPT equalled the most probable outcome for the human sample in both practice problems and transfer problems as well as upon their combination. Additionally, ChatGPT answer combinations were among the 5% of most probable outcomes for the human sample both when considering practice problems and pooled problem sets. These findings demonstrate that ChatGPT performance on both set of problems was in line with the mean rate of success of human subjects, indicating that it performed reasonably well. Conclusions: The use of transformer architecture and self-attention in ChatGPT may have helped to prioritize inputs while predicting, contributing to its potential in verbal insight problem-solving. ChatGPT has shown potential in solving insight problems, thus highlighting the importance of incorporating AI in psychological research. However, it is acknowledged that open challenges still exist. Indeed, further research is needed to fully understand the capabilities and limitations of AI in insight problem-solving.

In this paper we intend to present a dataset that contain a collection of tweets generated as reactions of the release of 50 different movies. The dataset can be used for gaining useful insights regarding the conversation that is generated around a particular movie. It is particularly suitable for conducting sentiment analysis and other NLP techniques. The dataset contains approximately 2.5 million tweets with their related meta data and cover 50 movies. For each movie, its IMDb rating is included. The movies are the 25 releases with the highest number of votes during 2020 and 2021. The collected tweets represent the reactions of the twitter community during the first week of the release date in US of that particular movie. The tweets per movie ranged from 1.000 to approximately 200.000 tweets with an average of 50.000 per release. We used The Internet Archive Wayback Machine in order to retrieve the IMDb movie rating after one week of the US release date. The tweets and related metadata have been collected using the Tweet Downloader tool.

The term low-resourced has been tossed around in the field of natural language processing to a degree that almost any language that is not English can be called "low-resourced"; sometimes even just for the sake of making a mundane or mediocre paper appear more interesting and insightful. In a field where English is a synonym for language and low-resourced is a synonym for anything not English, calling endangered languages low-resourced is a bit of an overstatement. In this paper, I inspect the relation of the endangered with the low-resourced from my own experiences.

The dataset reports a collection of earnings call transcripts, the related stock prices, and the related sector index. It contains a total of 188 transcripts, 11970 stock prices, and 1196 sector index values. Furthermore, all of these data originated in the period 2016-2020 and are related to the NASDAQ stock market. The data have been collected using Yahoo Finance and Thomson Reuters Eikon. Specifically, Yahoo Finance offered daily stock prices and traded volume. At the same time, Thomson Reuters Eikon has been used as source for the earnings call transcripts. The dataset can be used as a benchmark for the evaluation of several NLP techniques as well as machine learning algorithms for understanding their potential for financial applications. Moreover, it is also possible to expand the dataset by extending the period in which the data originated following a similar procedure.

In this review paper, we discuss the use of BERT, one of the most well-liked deep learning-based language models. The model's operation mechanism, key areas of applicability to text analytics tasks, comparisons with related models for each activity, and a description of certain proprietary models are all covered in this work. The data from several dozen original scientific studies that have been published in the last few years and have garnered the greatest interest from the scientific community were systematized in order to prepare this review. All researchers and students who wish to learn about the most recent developments in the field of natural language text analysis may find this survey helpful. Bidirectional Encoder Representations from Transformers, or BERT for short, is the subject of a thorough investigation that we present. The area of natural language processing holds significant importance in the creation of intelligent systems. To do a variety of activities, one must comprehend the sentence's correct meaning in order to produce the desired result. Computers have a hard time understanding languages because of how context constantly changes. The main challenge in natural language processing tasks is getting computers to understand text context, and BERT is seen as a revolution in this regard. It picks up the language and its meaning in a manner that is quite similar to how the human brain processes meaning from sentences. Its capacity to identify a word from both the left and right contexts of a sentence makes it special. A new era in the perception and comprehension of natural languages has been ushered in with the development of BERT, which could help computers understand natural languages more fully. This study aims to provide readers with a deeper knowledge of the BERT language model and how it is applied to different NLP tasks.

This article presents a state-of-the-art system to extract and synthesize causal statements from company reports into a directed causal graph. The extracted information is organized by the relevance to different stakeholder groups’ benefits (customers, employees, investors, and the community/environment). The presented method of synthesizing extracted data into a knowledge graph comprises a framework that can be used for similar tasks in other domains, e.g. medical information. The current work addresses the problem of finding, organizing, and synthesizing a view of the cause-and-effect relationships based textual data, in order to inform and even prescribe the best actions that may affect target business outcomes related to different stakeholders’ benefits (customers, employees, investors, and the community/environment).

In recent years, news media has been greatly disrupted by the potential of technologically driven approaches in the creation, production, and distribution of news products and services. Artificial intelligence (AI) has emerged from the realm of science fiction and has become a very real tool that can aid society in addressing many issues, including the challenges faced by the news industry. The ubiquity of computing has become apparent and has demonstrated the different approaches that can be achieved using AI. We analyzed the news industry’s AI adoption based on the seven subfields of AI: (i) machine learning; (ii) computer vision (CV); (iii) speech recognition; (iv) natural language processing (NLP); (v) planning, scheduling, and optimization; (vi) expert systems; and (vii) robotics. Our findings suggest that three subfields are being developed more in the news media: machine learning, computer vision, as well as planning, scheduling, and optimization. Other areas have not been fully deployed in the journalistic field. Most AI news projects rely on funds from tech companies such as Google. This limits AI’s potential to a small number of players in the news industry. We make conclusions by providing examples of how these subfields are being developed in journalism and present an agenda for future research.

Wikipedia is the most popular and the largest user-generated source of knowledge on the Web. Quality of the information in this encyclopedia is often questioned. Therefore, Wikipedians have developed an award system for high quality articles, which follows the specific style guidelines. Nevertheless, more than 1.2 million articles in Polish Wikipedia are unassessed. This paper considers over 100 linguistic features to determine the quality of Wikipedia articles in Polish language. We evaluate our models on 500,000 articles of Polish Wikipedia. Additionally, we discuss the importance of linguistic features for quality prediction.

Social networks have captured the attention of many people worldwide. However, these services have also attracted a considerable number of malicious users whose purpose is to compromise digital assets of other members by using messages as an attack vector to execute different variants of cyberattacks against them. Therefore, this work presents an approach based on Natural Language Processing tools and a Convolutional Neural Network architecture to detect and classify, on social network messages, four types of cyberattacks, such as malware, phishing, spam, and even one whose purpose is deceiving the user into spreading malicious messages to other users, which in this work is identified as bot attacks. One notable feature of this work is that it analyzes textual content without depending on any characteristics from a specific social network, making its analysis independent from particular data sources. Finally, this work was tested on real data, demonstrating its results in two stages. The first detects the existence of any of the four cyberattacks within the message, obtaining an accuracy value of 0.91. After detecting a message as a cyberattack, the next stage is to classify it into one of the four types of cyberattack, achieving an accuracy value of 0.82.

As the echoes of ChatGPT's remarkable success continue to permeate the AI community, its formidable successor, GPT-4, has emerged, showing off a wealth of novel features. In this concise paper, we elucidate the capabilities of GPT-4 and conduct a comparative analysis with its predecessor, ChatGPT, offering insights into their relative strengths and advancements in the rapidly evolving field of generative AI. We also present a comprehensive summary of the major performance results reported by OpenAI on GPT-4 across various Natural Language Processing (NLP) tasks. We place great emphasis on the innovative advancements offered by GPT-4 in comparison to its predecessors. Our focus is on highlighting its remarkable performance while also mentioning its limitations. The purpose of this paper is to deliver a succinct understanding of the new features and performance benchmarks of GPT-4.

Benchmarks for general language understanding have been rapidly developing in recent years of NLP research, particularly because of their utility in choosing strong-performing models for practical downstream applications. While benchmarks have been proposed in the legal language domain, virtually no such benchmarks exist for privacy policies despite their increasing importance in modern digital life. This could be explained by privacy policies falling under the legal language domain, but we find evidence to the contrary that motivates a separate benchmark for privacy policies. Consequently, we propose PrivacyGLUE as the first comprehensive benchmark of relevant and high-quality privacy tasks for measuring general language understanding in the privacy language domain. Furthermore, we release performances from multiple transformer language models and perform model-pair agreement analysis to detect tasks where models benefited from domain specialization. Our findings show the importance of in-domain pretraining for privacy policies. We believe PrivacyGLUE can accelerate NLP research and improve general language understanding for humans and AI algorithms in the privacy language domain, thus supporting the adoption and acceptance rates of solutions based on it.

Requirements are predominantly written in Natural Language (NL), which makes them accessible to stakeholders with varying degrees of experience, as compared to a model-based language which requires special training. However, despite its benefits, NL can introduce ambiguities and inconsistencies in requirements, which may eventually result in system quality degradation and system failure altogether. The system complexity that characterizes current systems warrants an integrated and comprehensive approach to system design and development. This need has brought about a paradigm shift towards Model-Based Systems Engineering (MBSE) approaches to system design and a departure from traditional document-centric methods. While, MBSE shows great promise, the ambiguities and inconsistencies present in NL requirements hinder their conversion to models directly. The field of Natural Language Processing (NLP) has demonstrated great potential in facilitating the conversion of NL requirements into a semi-machine-readable format that enables their standardization and use in a model-based environment. A first step towards standardizing requirements consists of classifying them according to the ``type'' (design, functional, performance, etc.) they represent. To that end, a language model capable of classifying requirements needs to be fine-tuned on labeled aerospace requirements. This paper presents the development of an annotated aerospace requirements corpus and its use to fine-tune BERT$_\text{BASE-UNCASED}$ to obtain aeroBERT-Classifier: a new language model for classifying aerospace requirements into design, functional, or performance requirements. A comparison between aeroBERT-Classifier and bart-large-mnli (zero-shot text classification) showcased the superior performance of aeroBERT-Classifier on classifying aerospace requirements despite being fine-tuned on a small labeled dataset.

Introduction: Around a million people are reported to die by suicide every year, and due to the stigma associated with the nature of the death, this figure is usually assumed to be an underestimate. Suicide may be prevented if prompt intervention is taken to mitigate risk. Machine learning and artificial intelligence-based modelling, such as natural language processing (NLP) and other text analytics approaches, has the potential to become a major technique for the detection, diagnosis, and treatment of people who are suffering from mental health issues. The primary aims of this research are to determine whether NLP techniques have been utilised in the field of suicide prevention, and if so, were they effective? What were their limitations? Methods: PubMed, EMBASE, MEDLINE, PsycInfo, and Global Health databases were searched for studies that reported use of NLP for suicide ideation or self-harm. Thematic analysis was used to synthesise and analyse the included studies. Findings were reported using the Preferred Reporting Items for Systematic Reviews and Meta-Analysis (PRISMA) statement, and the Mixed Methods Appraisal Tool (MMAT) was used in assessing paper quality. Result: The preliminary search of five databases generated 387 results. Removal of duplicates resulted in 158 potentially suitable studies. Twenty papers were finally included in this review. Discussion: Studies show that combining structured and unstructured data in NLP data modelling yielded more accurate results than utilizing either alone. Also, to reduce suicides, people with mental problems must be continuously and passively monitored. Further, NLP and other machine learning/artificial intelligence technologies can be used to address health inequities and electronic health records provide valuable data for creating suicide risk tools. Finally, Online, social media, and smartphone applications can be leverage in detecting people with suicide ideation. Conclusion: The use of artificial intelligence and machine learning opens new avenues for considerably guiding risk prediction and advancing suicide prevention frameworks. The review's analysis of the included research revealed that the use of NLP may result in low-cost and effective alternatives to existing resource-intensive methods of suicide prevention. To summarise, there is substantial evidence that NLP is useful in identifying people who have suicide ideation.

Social networking applications such as Twitter have increasingly gained significance in terms of socio-economic, political, and religious as well as entertainment sectors. This in turn, has witnessed a wide gamut of information explosion in the social networking realm that can tend to be both useful as well as misleading at the same point of time. Spam detection is one such solution that caters to this problem through identification of irrelevant users and their data. However, existing research has so far laid primary focus on user profile information through activity detection and relevant techniques that may underperform when these profiles exhibit characteristics of temporal dependency, poor reflection of generated content from the user profile, etc. This is the primary motivation for this paper that addresses the aforementioned problem of user profiles by focusing on both profile information and content-based spam detection. To this end, this work delivers three significant contributions. Firstly, exhaustive use of Natural language processing (NLP) techniques has been rendered towards creation of a new comprehensive dataset with a wide range of content-based features. Secondly, this dataset has been fed into a customized state-of-art hybrid machine learning model that has been exclusively built using a combination of both machine learning and deep learning techniques. Extensive simulation based analysis not only records over 98% accuracy but also establishes the practical applicability of this proposal by proving that modeling based on the mixed profile and content-generated data is more capable of spam detection in contrast to each of these standalone approaches. Finally, a novel methodology based on logistic regression is proposed and supported by analytical formulations. This paves the way for the custom-built dataset to be analyzed and corresponding probabilities to be obtained that differentiate legitimate users from spammers. The obtained mathematical outcome can henceforth be used for future prediction of user categories through appropriate parameter tuning for any given dataset. This makes our method a truly generic one capable of identifying and classifying different user categories.

An article's tone and framing not only influence an audience's perception of a story but may also reveal attributes of author identity and bias. Building upon prior media, psychological, and machine learning research, this neural network-based system detects those writing characteristics in ten news agencies' reporting, discovering patterns that, intentional or not, may reveal an agency's topical perspectives or common contextualization patterns. Specifically, learning linguistic markers of different organizations through a newly released open database, this probabilistic classifier predicts an article's publishing agency with 74% hidden test set accuracy given only a short snippet of text. The resulting model demonstrates how unintentional 'filter bubbles' can emerge in machine learning systems and, by comparing agencies' patterns and highlighting outlets' prototypical articles through an open source exemplar search engine, this paper offers new insight into news media bias.

Large Language Models (LLMs) have revolutionized the field of Artificial Intelligence with their ability to understand and generate natural language discourse. This has led to the use of LLMs in various creative fields such as music, art, and storytelling, which has sparked a debate on the impact of LLMs on human creativity. This article explores the cyclic effect of LLMs on human creativity, where LLMs can generate an ever-evolving cycle of creative output from both humans and machines. The article also highlights the importance of responsible and ethical use of LLMs, including privacy and copyright issues with the training data used by LLMs. The article emphasizes the need for transparency, data security measures, and AI governance policies to protect user data and ensure the safe use of LLMs. It also calls for the development of educational materials and resources to increase public understanding of LLMs and their ethical implications. The article concludes by highlighting the potential of LLMs as powerful tools for communication and education, but also emphasizes the need for ethical considerations to ensure the responsible and beneficial use of LLMs in society.

The classification of goods involved in international trade in Brazil is based on the Mercosur Common Nomenclature (NCM). The classification of these goods represents a real challenge due to the complexity involved in assigning the correct category codes especially considering the legal and fiscal implications of misclassification. This work focuses on the training of a classifier based on Bidirectional En-coder Representations from Transformers (BERT) for the tax classification of goods with NCM codes. In particular, this article presents results from using a specific Portuguese Language tuned BERT model as well results from using a Multilingual BERT. Experimental results justify the use of these models in the classification process and also that the language specific model has a slightly better performance.

To keep its business reliable, Google is concerned to ensure quality of apps on the store. One crucial aspect concerning quality is security. Security is achieved through Google Play protect and anti-malware solutions. However, they are not totally efficient since they rely on application features and application execution threads. Google provides additional elements to enable consumers to collectively evaluate applications providing their experiences via reviews or showing their satisfaction through rating. The latter is more informal and hides details of rating whereas the former is textually expressive but requires further processing to understand opinions behind. Literature lacks approaches which mine reviews through sentiment analysis to extract useful information to improve security aspects of provided applications. This work goes in this direction and in a fine-grained way, investigates in terms of confidentiality, integrity, availability and authentication (CIAA). While assuming that reviews are reliable and not fake, the proposed approach determines review polarities based on CIAA-related keywords. We rely on the popular classifier Naive Bayes to classify reviews into positive, negative and neutral sentiment. We then provide an aggregation model to fusion different polarities to obtain application global and CIAA reputations. Quantitative experiments have been conducted on 13 applications including e-banking, live messaging and anti-malware apps with a total of 1050 security-related reviews and 7.835.322 functionality-related reviews. Results show that 23% of applications (03 apps) have a reputation greater than 0.5 with an accent on integrity, authentication and availability, while the remaining 77% has a polarity under 0.5. Developers should make lot of efforts in security while developing codes and that more efforts should be made to improve confidentiality reputation. Results also show that applications with good functionality-related reputation generally offer bad security-related reputation. This situation means that even if the number of security reviews is low, it does not mean that security aspect is not a consumer preoccupation. Unlike, developers put much more time to test whether applications works without errors even if they include possible security vulnerabilities. A quantitative comparison against well-known rating systems reveals effectiveness and robustness of CIAA-RepDroid to repute apps in terms of security. CIAA-RepDroid can be associated to existing rating solutions to recommend developers exact CIAA aspects to improve within source codes.

Comments are exploited by product vendors to measure satisfaction of consumers. With the advent of Natural Language Processing (NLP), comments on Google Play can be processed to extract knowledge on applications such as their reputation. Proposals in that direction are either informal or interested merely on functionality. Unlike, this work aims to determine reputation of Android applications in terms of confidentiality, integrity, availability and authentication (CIAA). This work proposes a model of assessing app reputation relying on sentiment analysis and text analysis of comments. While assuming that comments are reliable, we collect Google Play applications subject to comments which include security keywords. An in-depth analysis of keywords based on Naive Bayes classification is made to provide polarity of any comment. Based on comment polarity, reputation is evaluated for the whole application. Experiments made on real applications including dozens to billions of comments, reveal that developers lack to make efforts to guarantee CIAA services. A fine-grained analysis shows that not security reputed applications can be reputed in specific CIAA services. Results also show that applications with negative security polarities display in general positive functional polarities. This result suggests that security checking should include careful comment analysis to improve security of applications.

Conversational artificial intelligence (AI) has shown strong capabilities in providing low-cost and timely interventions for a wide range of people and increasing well-being. Therefore, this study examined ChatGPT’s efficacy in conducting psychological counseling and its potential for providing accessible psychological interventions, especially in school settings. This study assessed the strengths and limitations of AI to inform future research. Data were generated from ChatGPT’s responses to 80 counseling questions that college students asked during a school counseling setting. All the responses generated during these simulated counseling sessions were then analyzed using three primary metrics—warmth, empathy, and acceptance—following APA guidelines. The analysis adopted several natural language processing methodologies for emotion detection and empathy measurement to quantify ChatGPT’s high efficacy in presenting the appropriate emotions and reactions for counseling. Some responses demonstrated randomness, which is crucial for consideration regarding the use of ChatGPT or relevant technology in psychological counseling. The Discussion section also highlights future directions in the application of conversational AI to enhance students’ mental health.

The dominance of social media has added to the channels of bullying to perpetrators. Unfortunately, cyberbullying (CB) is the most prevalent phenomenon in today’s cyber world and is a severe threat to the mental and physical health of citizens. This opens the need to develop a robust system to prevent bullying content from online forums, blogs, and social media platforms to manage the impact in our society. Several machine learning (ML) algorithms have been proposed for this purpose. However, their performances are not consistent due to high class imbalance issue and generalisation. In recent years, large language models (LLM) like BERT and RoBERTa have achieved state of the art (SOTA) results in several natural language processing (NLP) tasks. Unfortunately, the LLMs have not been applied extensively. In our paper, we explored the use of these models for cyberbullying (CB) detection. We have prepared a new dataset (D2) from existing studies (Formspring and Twitter). Our experimental results for dataset D1 and D2 showed RoBERTa outperformed other models.

Since the release of ChatGPT, numerous studies have highlighted the remarkable performance of ChatGPT, which often rivals or even surpasses human capabilities in various tasks and domains. However, this paper presents a contrasting perspective by demonstrating an instance where human performance excels in typical tasks suited for ChatGPT, specifically in the domain of computer programming. We utilize the IEEExtreme Challenge competition as a benchmark — a prestigious, annual international programming contest encompassing a wide range of problems with different complexities. To conduct a thorough evaluation, we selected and executed a diverse set of 102 challenges, drawn from five distinct IEEExtreme editions, using three major programming languages: Python, Java, and C++. Our empirical analysis provides evidence that contrary to popular belief, human programmers maintain a competitive edge over ChatGPT in certain aspects of problem-solving within the programming context. In fact, we found that the average score obtained by ChatGPT on the set of IEEExtreme programming problems is 3.9 to 5.8 times lower than the average human score, depending on the programming language. This paper elaborates on these findings, offering critical insights into the limitations and potential areas of improvement for AI-based language models like ChatGPT.

This article presents a dataset of tweets in the Urdu language. There are 1,140,824 tweets in the dataset, collected from Twitter for September and October 2020. This large-scale corpus of tweets is generated by performing pre-processing which includes removing columns containing user information, retweet’s count, followers information, duplicate tweets, removing unnecessary punctuation, links, symbols, and spaces, and finally extracting emojis if present in the tweet text. In the final dataset each tweet record contains columns for tweet id, text, and emoji extracted from the text with a sentiment score. Emojis are extracted to validate Machine Learning models used for the multilingual sentiment and behavior analysis. These are extracted using a Python script that searches for an emoji from the list of 751 most frequently used emojis. If an emoji is present in the text, a column with the emoji description and sentiment score is added.

In this paper, we propose "Synergized Efficiency Optimization for Large Language Models" (SEO-LLM), a groundbreaking approach that integrates advanced data utilization and model compression techniques to significantly enhance the performance, efficiency, and scalability of large language models (LLMs). Our method synergistically combines Adaptive Data Augmentation (ADA), Transfer- Active Learning (TAL), Adaptive Iterative Pruning (AIP), and Synergistic Quantization and Distillation (SQD). These components work together to reduce the training data requirement by 30%, compress model size by 67.6%, and improve inference speed by up to 50%, while preserving or even enhancing model accuracy across various NLP tasks. ADA dynamically adjusts augmentation strategies to optimize model generalization, while TAL leverages pre-trained models to focus learning on the most informative data samples. AIP intelligently prunes less significant weights, and SQD harmonizes quantization with knowledge distillation to achieve high compression rates without significant performance loss. The synergy between these techniques makes SEO-LLM a robust solution for deploying LLMs in resource-constrained environments, maintaining state-of-the-art performance with a fraction of the computational and data resources.

The large quantity of information retrieved from communities, public data repositories, web pages, or data mining can be sparsed and poorly classified. This work shows how to employ unsupervised classification algorithms such as K-means proper to classify user reviews into their closest category, forming a balanced data set. Moreover, we found that the text vectorization technique significantly impacts the clustering formation, comparing TF-IDF and Word2Vec. The value for mapping a cluster with movie genre was 81.34% ± 20.48 of the cases when the TF-IDF was applied, whereas Word2Vec only yielded a 53.51% ± 24.1. In addition, we highlight the impact of the removal of stop-words. Thus, we detected that pre-compiled lists are not the best method to remove stop-words before clustering because there is much ambiguity, centroids are poorly separated, and only 57% of clusters could match a movie genre. Thus, our proposed approach achieved a 94% of accuracy. After analyzing the classifiers’ results, we appreciated a similar effect when divided by the stop-words method removal. Statistically significant changes were observed, especially in precision metric and Jaccard scores in both classifiers, using custom-generated stop lists rather than pre-compiled ones. Reclassifying sparse data is strongly recommended as using custom-generated stop lists.

The Kuwaiti dialect is a particular dialect of Arabic spoken in Kuwait; it differs significantly from standard Arabic and the dialects of neighboring countries in the same region. Few research papers with a focus on the Kuwaiti dialect have been published in the field of NLP. In this study, we created Kuwaiti dialect language resources using Q8VaxStance, a vaccine stance labeling system for a large dataset of tweets. This dataset will fill this gap and provide a valuable resource for researchers studying vaccine hesitancy in Kuwait. Furthermore, it will contribute to the Arabic natural language processing field by providing a dataset for developing and evaluating machine learning models for stance detection in the Kuwaiti dialect. The proposed vaccine stance labeling system combines the benefits of weak supervised learning and zero-shot learning; for this purpose, we implemented 52 experiments on 42815 unlabeled tweets extracted between December 2020 and July 2022. The results of the experiments show that using keyword detection in conjunction with zero-shot model labeling functions is significantly better than using only keyword detection labeling functions or just zero-shot model labeling functions. Furthermore, using the Arabic language in both the labels and prompt or a mix of Arabic labels and an English prompt is statistically significant compared to using English in both the labels and prompt for the total number of generated labels evaluation metric. Finally, the best accuracy for Macro-F1 values were found in the experiments KHZSLF-EE4 and KHZSLF-EA1, with values of 0.83 and 0.83, respectively. And, for the total automatically labeled data evaluation metric, experiment KHZSLF-EE4 labeled 42,270 tweets, while experiment KHZSLF-EA1 was able to generate 42,764 labels.

Election outcomes have been predicted in the past with the help of various state-of-the-art language models. Sentiment analysis helps in establishing the opinions of the public about a particular subject, a popular experiment known as opinion mining. Twitter has grown in popularity and proven to be a key tool in mining people’s sentiments concerning election and other trending subjects of interest. The outcome of the just concluded Presidential election in Nigeria shifts the focus on Lagos State governorship election. In this study, we propose a Bidirectional Encoder Representations from Transformers (BERT) model for the sentiment analysis of governorship election in Lagos State Nigeria using Twitter data. A total of 800,000 personal and public tweets were scraped from twitter concerning the three prominent contesting candidates using carefully selected search queries. The tweets were preprocessed to avoid noise and inconsistencies. The preprocessed tweets were passed into the pretrained and finetuned BERT model. The result was analyzed to establish the sentiments of the public about the candidates. The social networks of the candidates were also analyzed. The parameter-tuning yield different results with different learning rates (LR). Results showed that the learning rate at 1e-7 gave the best performance and that the smaller the learning rate, the higher the accuracy but the larger the epoch size, the higher the accuracy.

Introduction: Social media platforms such as Facebook, LinkedIn, Twitter, among others have been used as a tool for staging protests, opinion polls, campaign strategy, medium of agitation and a place of interest expression especially during elections. Past studies have established people’s opinion elections using social media posts. The advent of state-of-the-art algorithms for unstructured text processing implies tremendous progress in natural language processing and understanding. Aim: In this work, a Natural Language framework is designed to understand Nigeria 2023 presidential election based on public opinion using Twitter dataset. Methods: Raw datasets concerning discourse around Nigeria 2023 elections from Twitter of 2,059,113 18 dimensions were collected. Sentiment analysis was performed on the preprocessed dataset using three different machine learning models namely: Long Short-Term Memory (LSTM) Recurrent Neural Network, Bidirectional Encoder Representations from Transformers (BERT) and Linear Support Vector Classifier (LSVC) models. Personal tweet analysis of the three candidates provided insight on their campaign strategies and personalities while public tweet analysis established the public’s opinion about them. The performance of the models was also compared using accuracy, recall, false positive rate, precision and F-measure. Results: LSTM model gave an accuracy, precision, recall, AUC and f-measure of 88%, 82.7%, 87.2% , 87.6% and 82.9% respectively; the BERT model gave an accuracy, precision, recall, AUC and f-measure of 94%, 88.5%, 92.5%, 94.7% and 91.7% respectively while the LSVC model gave an accuracy, precision, recall, AUC and f-measure of 73%, 81.4%, 76.4%, 81.2% and 79.2% respectively. Conclusion: The experimental results show that sentiment analysis and other Natural Language Processing tasks can aid in the understanding of the social media space. Results also revealed the leverage of each aspirant towards winning the election. We conclude that sentiment analysis can form a general basis for generating insights for election and modeling election outcomes.

Natural language Processing (NLP) has significantly transformed in the last decade, especially in the field of Language Modeling. Large Language Models (LLMs) have achieved SOTA performances on Natural Language Understanding (NLU) and Natural Language Generation (NLG) tasks by learning language representation in self-supervised ways. This paper provides a comprehensive survey to capture the progression of advances in Language Models. In this paper, we examine the different aspects of Language Models, which started with a few million parameters but have reached the size of a trillion in a very short time. We also look at how these LLMs transitioned from task-specific to task-independent to task-and-language-independent architectures. This paper extensively discusses different pre-training objectives, benchmarks, and transfer learning methods used in LLMs. It also examines different fine-tuning and In-Context learning techniques used in downstream tasks. It also explores how LLMs can perform well across many domains and datasets if sufficiently trained on a large and diverse dataset. Next, it discusses how, over time, the availability of cheap computational power and large datasets have improved LLM’s capabilities and raised new challenges. As part of our study, we also inspect LLMs from the lens of scalability to see how their performance is affected by the model’s depth, width, and data size. Lastly, we provide an empirical comparison of existing trends and techniques and a comprehensive analysis of where the field of LLM currently stand.

(1) Background: Information overload challenges decision-making in the Industry 4.0 era. While Natural Language Processing (NLP), especially Automatic Text Summarization (ATS), offers solutions, issues with factual accuracy persist. This research bridges cognitive neuroscience and NLP, aiming to improve model interpretability. (2) Methods: This research examined four fact extraction techniques: dependency relation, named entity recognition, part-of-speech tagging, and TF-IDF, in order to explore their correlation with human EEG signals. Representational Similarity Analysis (RSA) was applied to gauge the relationship between language models and brain activity. (3) Results: Named entity recognition showed the highest sensitivity to EEG signals, marking the most significant differentiation between factual and non-factual words with a score of -0.99. The dependency relation followed with -0.90, while part-of-speech tagging and TF-IDF resulted in 0.07 and -0.52, respectively. Deep language models such as GloVe, BERT, and GPT-2 exhibited noticeable influences on RSA scores, highlighting the nuanced interplay between brain activity and these models. (4) Conclusions: Our findings emphasize the crucial role of named entity recognition and dependency relations in fact extraction and demonstrate the independent effects of different models and TOIs on RSA scores. These insights aim to refine algorithms to reflect human text processing better, thereby enhancing ATS models’ factual integrity.

Refinery planning optimization is a challenging problem as regards handling the nonconvex bilinearity mainly due to pooling operations in processes such as crude oil distillation and product blending. This work investigates the performance of several representative piecewise-linear (or piecewise-affine) relaxation schemes (referred to as McCormick, bm, nf5, nf6t, and de (which is a new approach proposed based on eigenvector decomposition) that mainly give rise to mixed-integer optimization programs to convexify a bilinear term using predetermined univariate partitioning for instances of uniform and non-uniform partition sizes. Computational results show that applying these schemes give improved relaxation tightness than only applying convex and concave envelopes as estimators. Uniform partition sizes typically perform better in terms of relaxation solution quality and convergence behavior. It is also seen that there is a limit on the number of partitions that contributes to relaxation tightness, which does not necessarily correspond to a larger number of partitions, while a direct relation between relaxation size and tightness does not always hold for non-uniform partition sizes.

Colonoscopy is used for colorectal cancer (CRC) screening. Extracting details of the colonoscopy findings from free text in electronic health records (EHRs) can be used to determine patient risk for CRC and colorectal screening strategies. In this study, we developed and evaluated the accuracy of a deep learning model framework to extract information for the clinical decision support system to analyze relevant free-text colonoscopy reports, including indications, pathology, and findings notes. The Bio-Bi-LSTM-CRF framework was developed using Bidirectional Long Short-term Memory (Bi-LSTM) and Conditional Random Fields (CRF) to extract several clinical features from these free-text reports, including indications for the colonoscopy, findings during the colonoscopy, and pathology of the resected material. We then trained the Bio-Bi-LSTM-CRF and existing Bi-LSTM-CRF models on 80% of 4,000 manually annotated notes obtained from the colonoscopy reports of 3,867 patients. The clinical notes were from a group of patients aged over 40 years old enrolled in four Veterans Affairs Medical Centers. A total of 10% of the remaining annotated notes were used to train hyperparameter, while the remaining 10% were used to evaluate the accuracy of our model (Bio-Bi-LSTM-CRF) and to compare the results with the outcomes obtained using Bi-LSTM-CRF. The results of our experiments showed that the bidirectional encoder representations by integrating dictionary function vector from Bio-Bi-LSTM-CRF and strategies character sequence embedding approach is an effective way to identify colonoscopy features from EHR-extracted clinical notes. Therefore, the Bio-Bi-LSTM-CRF model is concluded to be capable of creating new opportunities to identify patients at risk for colon cancer and to study their health outcomes.

We present a novel benchmarking methodology for Large Language Models (LLMs) to evaluate their susceptibility to hallucinations, thereby determining their reliability for real-world applications involving greater responsibilities. This method, called Deception-Based Benchmarking, involves testing the model with a task that requires composing a short paragraph. Initially, the model performs under standard conditions. Then, it is required to begin with a misleading sentence. Based on these outputs, the model is assessed on three criteria: accuracy, susceptibility, and consistency. This approach can be integrated with existing benchmarks or applied to new ones, thus facilitating a comprehensive evaluation of models across multiple dimensions. It also encompasses various forms of hallucination. We applied this methodology to several small opensource models using a modified version of MMLU, DB-MMLU1 . Our findings indicate that most current models are not specifically designed to self-correct when the random sampling process leads them to produce inaccuracies. However, certain models, such as Solar-10.7B-Instruct, exhibit a reduced vulnerability to hallucination, as reflected by their susceptibility and consistency scores. These metrics are distinct from traditional benchmark scores. Our results align with TruthfulQA, a widely used benchmark for hallucination. Looking forward, DB-benchmarking can be readily applied to other benchmarks to monitor the advancement of LLMs.

In the dynamic field of mental health care, the nuanced application of Artificial Intelligence (AI) through Natural Language Processing (NLP) and Automatic Speech Recognition (ASR) is a pivotal innovation in patient empowerment and service optimization. This study introduces a distinctive online therapy platform that capitalizes on the synergy of NLP and ASR to offer unprecedented levels of interactive and personalized therapeutic interventions. The architecture of our system is meticulously detailed, featuring an ASR component with an impressive Word Error Rate (WER) of 14% when trained on the diverse French subsets of the Mozilla Common Voice dataset, complemented by a high-precision NLP framework skilled in processing and responding to user inputs. The evaluation of our system highlights its efficacy in enhancing therapy sessions and user satisfaction, with an emphasis on the qualitative aspects of user feedback. The paper addresses challenges such as dataset representativeness and language model refinement and articulates the strategic solutions employed to overcome them. The paper concludes with forward-looking perspectives on AI's role in mental health services, advocating for the creation of sophisticated, language-specific datasets and models to satisfy the increasing demands of online therapy, reflecting a growing commitment of patients in the management of their therapy. This research underscores the transformative impact of AI in advancing mental health care into the digital age, representing a significant evolution over existing methodologies.

We live in a complex world characterised by complex people, complex times, and complex social, technological, and ecological environments. There is clear evidence that governments are failing at most public matters. The recent COVID-19 pandemic is a high example of global governance failure both at preventing such pandemics and managing the COVID-19 pandemic. It is time that all of us take responsibility and look into ways of collaboratively improving the governance of public matters, our matters. While there are many reasons for government failures, we believe the lack of information availability is a fundamental reason that limits the government’s ability to act smartly and allows the lack of transparency to creep into policy and action leading to corruption and failure. To this end, this paper introduces the concept of deep journalism, a data-driven deep learning-based approach for discovering multi-perspective parameters related to a topic of interest. We build three datasets (a newspaper, a technology magazine, and a Web of Science dataset) and discover the academic, industrial, public, governance, and political parameters for the transportation sector as a case study to introduce deep journalism and our tool DeepJournal (Version 1.0) that implements our proposed approach. We elaborate on 89 transportation parameters and hundreds of dimensions reviewing 400 technical, academic, and news articles. The findings related to the multi-perspective view of transportation reported in this paper show that there are many important problems seen by the public that industry and academia seem to not place their focus on. On the other hand, academia produces much broader and deeper knowledge on the subject such as a wide range of pollutions affecting the people and planet do not get to reach the public eye. Our deep journalism approach could find the gaps and highlight them to the public and other stakeholders.

Hate Speech Detection in Arabic presents a multifaceted challenge due to the broad and diverse linguistic terrain. With its multiple dialects and rich cultural subtleties, Arabic requires particular measures to address hate speech online successfully. To address this issue, academics and developers have used natural language processing (NLP) methods and machine learning algorithms adapted to the complexities of Arabic text. However, many proposed methods were hampered by a lack of a comprehensive dataset/corpus of Arabic hate speech. In this research, we propose a novel multi-class public Arabic dataset comprised of 403,688 annotated tweets categorized as extremely positive, positive, neutral, or negative based on the presence of hate speech. Using our developed dataset, we additionally characterize the performance of multiple machine learning models for Hate speech identification in Arabic Jordanian dialect tweets. Specifically, the Word2Vec, TF-IDF, and AraBert text representation models have been applied to produce word vectors. With the help of these models, we can provide classification models with vectors representing text. After that, seven Machine learning classifiers have been evaluated: Support Vector Machine (SVM), Logistic Regression (LR), Naive Bays (NB), Random Forest (RF), AdaBoost (Ada), XGBoost (XGB), and CatBoost (CatB). In light of this, the experimental evaluation revealed that, in this challenging and unstructured setting, our gathered and annotated datasets were rather efficient and generated encouraging assessment outcomes. This will enable academics to delve further into this crucial field of study.

This study aims to put forth a new method to study the socio-spatial boundaries by using georeferenced community-authored reviews for restaurants. In this study, we show that food choice, drink choice, and restaurant ambience can be good indicators of socio-economic status of the ambient population in different neighborhoods. To this end, we use Yelp user reviews to distinguish different neighborhoods in terms of their food purchases and identify resultant boundaries in 10 North American metropolitan areas. This data-set includes restaurant reviews as well as a limited number of user check-ins and rating in those cities. We use Natural Language Processing (NLP) techniques to select a set of potential features pertaining to food, drink and ambience from Yelp user comments for each geolocated restaurant. We then select those features which determine one’s choice of restaurant and the rating that he/she provides for that restaurant. After identifying these features, we identify neighborhoods where similar taste is practiced. We show that neighborhoods identified through our method show statistically significant differences based on demographic factors such as income, racial composition, and education. We suggest that this method helps urban planners to understand the social dynamics of contemporary cities in absence of information on service-oriented cultural characteristics of urban communities.

Undoubtedly, there is a potential impact of large language models like ChatGPT in revolutionizing information retrieval and knowledge discovery, particularly in the context of the vast amount of electronic material available. On another strong note, the current work offers a first time ever mathematical approach to accurately fine tune perplexity AI, which sets a giant step ahead towards accurate next generations AI. Having started this world leading discovery, the upper and lower bounds of perplexity AI, namely , , respectively, are obtained for the first-time ever. Concluding remarks combined with emerging open problems and next research phase are provided.

We live in the information age and, ironically, meeting the core function of journalism – i.e., to provide people access to unbiased information – has never been more difficult. This paper explores deep journalism, our data-driven Artificial Intelligence (AI) based journalism approach to study how the LinkedIn media could be useful for journalism. Specifically, we apply our deep journalism approach to LinkedIn to automatically extract and analyse big data to provide the public with information about labour markets, people’s skills and education, and businesses and industries from multi-generational perspectives. The Great Resignation and Quiet Quitting phenomena coupled with rapidly changing generational attitudes are bringing unprecedented and uncertain changes to labour markets and our economies and societies, and hence the need for journalistic investigations into these topics is highly significant. We combine big data and machine learning to create a whole machine learning pipeline and a software tool for journalism that allows discovering parameters for age dynamics in labour markets using LinkedIn data. We collect a total of 57,000 posts from LinkedIn and use it to discover 15 parameters by Latent Dirichlet Allocation algorithm (LDA) and group them into five macro-parameters, namely Generations-Specific Issues, Skills & Qualifications, Employment Sectors, Consumer Industries, and Employment Issues. The journalism approach used in this paper can automatically discover and make objective, cross-sectional, and multi-perspective information available to all. It can bring rigour to journalism by making it easy to generate information using machine learning and can make tools and information available so that anyone can uncover information about matters of public importance. This work is novel since none of the earlier works have reported such an approach and tool and leveraged it to use LinkedIn media for journalism and to discover multigenerational perspectives (parameters) for age dynamics in labour markets. The approach could be extended with additional AI tools and other media.

In this paper, we present a novel approach for managing the file system in Linux using a voice assistant. Our system allows users to perform file system operations such as creating directories, renaming files, and deleting files by issuing voice commands. We develop a voice assistant using Python libraries and integrate it with the file system in Linux. The voice assistant is capable of understanding natural language and executing commands based on the user's voice inputs. We conduct experiments to evaluate the performance of the system and demonstrate that our approach is effective and efficient in managing the file system using voice commands. Our system can enhance the accessibility and usability of the file system in Linux for individuals with disabilities or those who prefer a hands-free approach to file management.

Long unpunctuated texts containing complex linguistic sentences are a stumbling block to processing any low-resource languages. Thus, approaches that attempt to segment lengthy texts with no proper punctuation into simple candidate sentences are a vitally important preprocessing task in many hard-to-solve NLP applications. In this paper, we propose (PDTS) a punctuation detection approach for segmenting Arabic text, built on top of a multilingual BERT-based model and some generic linguistic rules. Furthermore, we showcase how PDTS can be effectively employed as a text tokenizer for unpunctuated documents (i.e., mimicking the transcribed audio-to-text documents). Experimental findings across two evaluation protocols (involving an ablation study and a human-based judgment) demonstrate that PDTS is practically effective in both performance quality and computational cost.

As digital communication becomes increasingly integral to personal and corporate activities, phishing attacks have emerged as a prevalent threat, ingeniously mimicking legitimate sources to illicitly acquire sensitive information. This research paper details the development of a sophisticated phishing detection application utilizing the DistilBERT-based model, finetuned on a diverse array of email datasets. The application significantly enhances the precision of phishing detection mechanisms, adeptly reducing the incidence of successful phishing attacks. Initial tests have demonstrated a precision rate of over 95% in detecting phishing emails, outperforming traditional rule-based filters substantially. The application exhibits robust defences against zero-day phishing attacks through its advanced machine learning framework, which dynamically adapts to emerging phishing strategies. This paper explores the methodology of developing the DistilBERT model, evaluates its efficacy against existing solutions, and discusses its implications for future cybersecurity practices. The study’s findings underscore the potential of AI-driven tools in transforming cybersecurity measures, offering a proactive approach to thwarting phishing attempts and safeguarding sensitive data.

In potato, high levels of nitrogen (N) can lead to excessive vegetative growth at the expense of tuber development, resulting in lower yield and poor quality tubers. We found that Solanum tuberosum CLE4 (StCLE4) is expressed most strongly in the roots on N-rich media and positively regulates root growth of potato in N-deficient conditions. We noted that StCLE4 functions as a negative regulator of normal shoot apex development similar to CLV3 in Arabidopsis. Transcriptomic analysis revealed that overexpression of StCLE4 results in repression of the StIT1 gene, a regulator of potato tuber initiation. Overexpressing StCLE4 stolons were transformed into branches that were similar to milder it1 phenotype. We also found that NIN-like proteins, key regulators of nitrate signaling, bind to the regulatory sequence of StIT1 in yeast one-hybrid assay. Taken together, our findings suggest that StCLE4 regulates shoot, root and stolon growth in potato.

Confusion, fear and mixed sentiments prevail in the minds of people towards what is arguably one of the most important of dynamics of modern human society: Artificial Intelligence (AI). This study aims to explore the contributions of news media towards this phenomenon - we analyze nearly seventy thousand recent news headlines on AI, using natural language processing (NLP) informatics methods, machine learning (ML) and large language models (LLMs) to draw insights and discover dominant themes. Our theoretical framework was derived from extant literature which posits the power of fear producing articles and news headlines which produce significant impacts on public behavior even when available in small quantities. We applied extensive textual informatics methods using word and phrase frequency analytics, sentiment analysis and human experts based thematic analysis to discover insights on AI phobia inducing news headlines. Our rigorous analysis of nearly seventy thousand headlines using multiple validation methods in NLP (exploratory informatics including BERT, Llama 2 and Mistral based topic identification), ML (supervised informatics) and LLMs (neural nets for sentiment classification, with BERT, Llama 2 and Mistral) demonstrates the presence of an unreasonable level of emotional negativity and fear inducing verbiage in AI news headlines. The framing of AI as being dangerous or as being an existential threat to humanity can have a profound impact on public perception, and the resulting AI phobia and confusion in public perceptions are inherently detrimental to the science of AI. Furthermore, this can also impact AI policy and regulations, and harm society. We conclude with a discussion deducing implications for society and make recommendations for education and policies that could support human identity and dignity.

The increased complexity of modern systems is calling for an integrated and comprehensive approach to system design and development and in particular, a shift towards Model-Based Systems Engineering (MBSE) approaches for system design. The requirements that serve as the foundation for these intricate systems are still primarily expressed in Natural Language (NL), which can contain ambiguities and inconsistencies that hinder their direct translation into models. The colossal developments in the field of Natural Language Processing (NLP) in general and Large Language Models (LLMs) in particular can serve as an enabler for the conversion of NL requirements into semi-machine-readable requirements. This is expected to facilitate their standardization and use in a model-based environment. This paper discusses a two-fold strategy for converting NL requirements into semi-machine-readable requirements using language models. The first approach involves creating a requirements table by extracting information from free-form NL requirements. The second approach is an agile methodology that facilitates the identification of boilerplate templates for different types of requirements based on observed linguistic patterns. For this study, three different LLMs were utilized. Two of these models were fine-tuned versions of Bidirectional Encoder Representations from Transformers (BERT), specifically aeroBERT-NER and aeroBERT-Classifier, which were trained on annotated aerospace corpora. Another LLM, called flair/chunk-english, was utilized to identify sentence chunks present in NL requirements. All three language models were utilized together to achieve the standardization of requirements. To demonstrate the effectiveness of the methodologies, requirements from Parts 23 and 25 of Title 14 Code of Federal Regulations (CFRs) were employed, and a total of two, five, and three boilerplate templates were identified for design, functional, and performance requirements, respectively.

The Global natural and manmade events are exposing the fragility of the tourism industry and its impact on the global economy. Prior to the COVID-19 pandemic, tourism contributed 10.3% to the global GDP and employed 333 million people but saw a significant decline due to the pandemic. Sustainable and smart tourism requires collaboration from all stakeholders and a comprehensive understanding of global and local issues to drive responsible and innovative growth in the sector. This paper presents an approach for leveraging big data and deep learning to dis-cover holistic, multi-perspective (e.g., local, cultural, national, and international) and objective information on a subject. Specifically, we develop a machine learning pipeline to extract parameters from academic literature and public opinions on Twitter, providing a unique and comprehensive view of the industry from both academic and public perspectives. The academic-view dataset was created from the Scopus database and contains 156,759 research articles from 2000 to 2022, which were modelled to identify 33 distinct parameters in 4 categories: Tourism Types, Planning, Challenges, and Media & Technologies. A Twitter dataset of 485,813 tweets was collected over 18 months starting March 2021 to August 2022 to showcase public perception of tourism in Saudi Arabia, which was modelled to reveal 13 parameters categorized into two broader sets: Tourist Attractions and Tourism Services. Discovering system parameters are re-quired to embed autonomous capabilities in systems and for decision-making and problem-solving during system design and operations. The proposed approach improves AI-based information discovery by extending the use of scientific literature, Twitter, and other sources for autonomous, dynamic optimizations of systems, promoting novel research in the tourism sector and contributing to the development of smart and sustainable societies. The paper also presents a comprehensive knowledge structure and literature review of the tourism sector based on over 250 research articles.

This research delves into the realm of predictive modeling within artificial intelligence (AI) and introduces an innovative ensemble approach designed to enhance prognostic precision. The proposed methodology, characterized by its ebullient nature, leverages the collective wisdom of diverse predictive models, synthesizing a comprehensive and robust framework. The pursuit of parsimony are paramount, underscoring the need for efficient model architectures that balance predictive acuracy and computational efficiency. Our study meticulously explores the amalgamation of diverse algorithms, encapsulating the intrinsic complexity of real-world phenomena. We navigate the intricate landscape of feature selection, algorithmic diversity, and model combination, fostering a holistic understanding of the prognostic process. The ebullient ensemble emerges as a dynamic solution, harnessing the synergy of constituent models while mitigating the risk of overfitting. To validate the efficacy of our approach, extensive experiments are conducted on diverse datasets, spanning domains such as healthcare, finance, and natural language processing. Comparative analyses demonstrate the superior predictive performance of our ensemble model in comparison to individual algorithms and traditional ensemble methods. Additionally, we delve into interpretability aspects, elucidating the underlying mechanisms that contribute to the model's prognostic prowess. Our research advances the frontier of predictive modeling in AI, offering a nuanced and sophisticated paradigm for prognostication. The ebullient ensemble approach stands as a testament to the synergy achievable through the amalgamation of diverse predictive models, providing a pragmatic and parsimonious avenue for enhanced prognostic acuracy in artificial intelligence applications.

Background: Open AI developed ChatGPT, a language model based on the GPT architecture, designed for text-based communication. Trained on diverse internet texts, ChatGPT generates contextually appropriate responses using machine learning. It understands input through analysis and context interpretation, generating coherent and contextually relevant responses. Interaction is possible through messaging platforms. Materials and Methods: In November 2023, we utilized ChatGPT 3.5, the default version at that time, to answer questions from the Italian National Residency Program Admission Tests (SSMs) of 2021, 2022, and 2023. The questions cover clinical, diagnostic, analytical, therapeutic, and epidemiological scenarios, sometimes accompanied by images. The study compared ChatGPT's answers to the official corrections on the Italian Ministry of University and Research (MUR) website. The scoring method used for evaluation was 1 point for correct answers, 0 points for unanswered questions, and -0.25 points for incorrect answers, reflecting the SSM test scoring system. Results: In summary, ChatGPT was tested with a total of 420 questions, 140 for each test. It achieved an overall accuracy of 80.48%, providing correct answers for 338 questions and incorrect answers for 82 questions. When faced with questions containing both text and images, it answered 55% correctly and 45% incorrectly. The model's performance varied over time, with an 82.14% accuracy rate in 2021 and 2022 (115 correct out of 140) and a 77.14% accuracy rate in 2023 (108 correct out of 140). Applying thisscoring method to the SSM test, ChatGPT would have scored 105 points in 2021 and 2022, and 100 points in 2023. Conclusions: ChatGPT has exhibited above-average performance in the last three SSM tests, highlighting its robust capability to interpret clinical scenarios and offer precise diagnostic and therapeutic guidance. Despite this, some limitations persist, notably the software's inability to interpret non-textual information.

Technological advancements and innovations have profoundly changed the lives of people giving rise to smart environments, cities, and societies. As homes are the building block of cities and societies, smart homes are critical to establishing smart living and are expected to play a key role in enabling smart cities and societies. The current academic literature and commercial advancements on smart homes have mainly focused on developing and providing smart functions for homes to provide security management and facilitate the residents in their various activities such as ambiance management. Homes are much more than physical structures, buildings, appliances, operational machines, and systems. Homes are composed of families and are inherently complex phenomena underlined by humans and their relationships with each other, subject to individual, intragroup, intergroup, and intercommunity goals. There is a clear need to understand, define, consolidate existing research, and actualize the overarching roles of smart homes, the roles of smart homes that would serve the needs of future smart cities and societies. This paper introduces our data-driven parameter discovery methodology and uses it to provide, for the first time, an extensive, rather fairly comprehensive, analysis of the families and homes landscape seen through the eyes of academics and the public using over a hundred thousand research papers and nearly a million tweets. We develop a methodology using deep learning, natural language processing (NLP), and big data analytics methods and apply it to automatically discover parameters that capture a comprehensive knowledge and design space of smart families and homes comprising social, political, economic, environmental, and other dimensions. The 66 discovered parameters and the knowledge space comprising 100s of dimensions are explained by reviewing and referencing over 300 articles from the academic literature and tweets. The knowledge and parameters discovered in this paper can be used to develop a holistic understanding of matters related to families and homes facilitating the development of better, community-specific, policies, technologies, solutions, and industries for families and homes, leading to strengthening families and homes, and in turn, empowering sustainable societies across the globe.

We assume that poetic devices have an implicit goal: producing an overall sound scheme that will induce the reader to associate intended and expressed meaning to the sound of the poem. Sounds may be organized into categories and assigned presumed meaning as suggested by traditional literary studies. In my work, I have extracted automatically the sound grids of all the sonnets by William Shakespeare and have combined them with the themes expressed by their contents. In a first experiment I have computed lexically and semantically based sentiment analysis obtaining an 80% of agreement. In a second experiment sentiment analysis has been substituted by Appraisal Theory thus obtaining a more fine-grained interpretation which in some cases contradicts the first one. The computation for the second poet - regarded by many critics the best of last century - includes both vowels and consonants. In addition, it combines automatic semantically and lexically based sentiment analysis with sound grids. The results produce visual maps that clearly separate poems into three clusters: negative harmony, positive harmony and disharmony where the latter instantiates the need by the poet to encompass the opposites in a desperate attempt to reconcile them.