<![CDATA[This study analyses user sentiment toward the ChatGPT application based on reviews collected from the Google Play Store. The goal of this research is to classify user opinions into positive and negative categories using the Support Vector Machine (SVM) algorithm. The dataset was obtained through web scraping and processed using several text preprocessing steps, including case folding, tokenization, stopword removal, and stemming. The TF-IDF method was applied to convert the text into numerical feature vectors suitable for machine learning models. A linear SVM model was used to perform sentiment classification due to its effectiveness in handling high-dimensional text data. The results of the evaluation show that the linear SVM provides stable and accurate performance when identifying sentiment in user reviews. The findings also indicate that TF-IDF features contribute significantly to improving model accuracy. Overall, this research concludes that SVM is a suitable and reliable method for sentiment analysis of application reviews. The outcomes can help developers understand user perceptions and improve the quality of the ChatGPT application based on the insights obtained]]>
Copyrights © 2025
