Article Per Year (5 Year)
p-Index From 2021 - 2026
0.23
P-Index
This Author published in this journals
All Journal International Journal of Applied Information Systems and Informatics
Alkamal, Chaerulsyah
Unknown Affiliation
Computer Science & IT

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

 1 
Text Mining-Based Sentiment Analysis of ChatGPT Users on X Platform Using Naïve Bayes Algorithm Alkamal, Chaerulsyah; Kurniadi, Dede
Journal of Applied Information System and Informatic (JAISI) Vol 3, No 2 (2025): November 2025
Publisher : Deparment Information System, Siliwangi University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37058/jaisi.v3i2.17062

Abstract

ChatGPT (Generative Pre-trained Transformer) is a natural language processing model based on Artificial Intelligence (AI) that is currently trending. ChatGPT is widely used by the public because it is considered very helpful in completing tasks or solving problems faced by society. However, as the use of ChatGPT grows, questions have arisen about how people perceive and respond to interactions with ChatGPT present. The use of ChatGPT not only creates opportunities but also new challenges in understanding user perceptions and sentiments toward this technology. For example, various controversies have emerged regarding the presence of ChatGPT. Therefore, this research aims to determine the sentiments of society, particularly among users of social media X, toward ChatGPT, and whether most of society views it positively, negatively, or neutrally. By conducting sentiment analysis and implementing Text Mining, the tendency of a particular sentiment or opinion, whether it leans toward positive, negative, or neutral, can be obtained relatively easily. The method used in this research is SEMMA (Sample, Explore, Modify, Model, Assess) with Naïve Bayes as the algorithm to be implemented. To evaluate the model, a Confusion Matrix is used. The sentiment analysis results show that out of a total of 1,314 data points, 39.4% were positive, 37.7% were neutral, and 22.9% were negative. The classification model achieved an accuracy of 72.78%, which is considered quite good.
Co-Authors Dede Kurniadi