Conti, D.; Gomez, C.E.; Jaramillo, J.G.; Ospina, V.E. Monitoring the Quality and Perception of Service in Colombian Public Service Companies with Twitter and Descriptive Temporal Analysis. Appl. Sci.2023, 13, 10338.
Conti, D.; Gomez, C.E.; Jaramillo, J.G.; Ospina, V.E. Monitoring the Quality and Perception of Service in Colombian Public Service Companies with Twitter and Descriptive Temporal Analysis. Appl. Sci. 2023, 13, 10338.
Conti, D.; Gomez, C.E.; Jaramillo, J.G.; Ospina, V.E. Monitoring the Quality and Perception of Service in Colombian Public Service Companies with Twitter and Descriptive Temporal Analysis. Appl. Sci.2023, 13, 10338.
Conti, D.; Gomez, C.E.; Jaramillo, J.G.; Ospina, V.E. Monitoring the Quality and Perception of Service in Colombian Public Service Companies with Twitter and Descriptive Temporal Analysis. Appl. Sci. 2023, 13, 10338.
Abstract
The use of the voice of the customer as a main input to guide decision making towards customer centricity strategies has become a necessity for companies. This research proposes a structured method of textual processing using the KDD (Knowledge Discovery Databases) methodology applied to the tweets of users of Colombian public sector companies, through the analysis of temporal sentiments and topic modeling to identify the areas in which actions should be taken to improve the perception of service. To fulfill such purpose, tweets from January to June 2022 are processed, followed by a temporal analysis of the evolution of the sentiment based on 3 enriched dictionaries; after, the LDA (Linear Discriminant Analysis) algorithm is implemented to find the areas with ailment for the user, in addition to propose a method to homologate the CIER (Comisión de Integración Energética Regional) survey. Finally, metrics are detailed to follow up the perception of the service. It is concluded that for the Acueducto the topic with the highest number of complaints is related to "Water truck request", for Enel "Servide Outages" and for Vanti: " Case solution and request information". Also, the homologation of 3 of the 5 pillars on which the CIER survey is based is presented.
Keywords
LDA; Topic Modeling; Twitter; Time Series; Sentiment Analysis; CIER
Subject
Computer Science and Mathematics, Artificial Intelligence and Machine Learning
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.
