Version 1
: Received: 13 September 2021 / Approved: 15 September 2021 / Online: 15 September 2021 (09:42:19 CEST)
How to cite:
Hossain, S.M.M.; Kamal, K.M.A.; Sen, A.; Sarker, I.H. TF-IDF Feature-Based Spam Filtering of Mobile SMS Using Machine Learning Approach. Preprints2021, 2021090251. https://doi.org/10.20944/preprints202109.0251.v1
Hossain, S.M.M.; Kamal, K.M.A.; Sen, A.; Sarker, I.H. TF-IDF Feature-Based Spam Filtering of Mobile SMS Using Machine Learning Approach. Preprints 2021, 2021090251. https://doi.org/10.20944/preprints202109.0251.v1
Hossain, S.M.M.; Kamal, K.M.A.; Sen, A.; Sarker, I.H. TF-IDF Feature-Based Spam Filtering of Mobile SMS Using Machine Learning Approach. Preprints2021, 2021090251. https://doi.org/10.20944/preprints202109.0251.v1
APA Style
Hossain, S.M.M., Kamal, K.M.A., Sen, A., & Sarker, I.H. (2021). TF-IDF Feature-Based Spam Filtering of Mobile SMS Using Machine Learning Approach. Preprints. https://doi.org/10.20944/preprints202109.0251.v1
Chicago/Turabian Style
Hossain, S.M.M., Anik Sen and Iqbal H. Sarker. 2021 "TF-IDF Feature-Based Spam Filtering of Mobile SMS Using Machine Learning Approach" Preprints. https://doi.org/10.20944/preprints202109.0251.v1
Abstract
Short Message Service (SMS) is becoming the secure medium of communication due to large-scale global coverage, reliability, and power efficiency. As person--to--person (P2P) messaging is less secure than application-to-person (A2P) messaging, anyone can send a message, leading to the attack. Attackers mistreat this opportunity to spread malicious content, perform harmful activities, and abuse other people, commonly known as spam. Moreover, such messages can waste a lot of time, and important messages are sometimes overlooked. As a result, accurate spam detection in SMS and its computational time are burning issues. In this paper, we conduct six different experiments to detect SMS spam from the dataset of 5574 messages using machine learning classifiers such as Multinomial Naïve Bayes (MNB) and Support Vector Machine (SVM), considering variations of \textit{Term Frequency-- Inverse Document Frequency (TF--IDF)} features for exploring the trade-off among accuracy, F1-score and computational time. The experiments achieve the best result of the accuracy of 98.50\%, F1--score of 98\%, and area under roc curve (AUC) of 0.97 for multinomial naïve bayes classifier with TF--IDF after stemming.
Keywords
Spam detection; SMS; Security; Machine learning
Subject
Computer Science and Mathematics, Information Systems
Copyright:
This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
