<![CDATA[User reviews on the Google Play Store contain a wide range of feedback regarding app usage. In the case of the Kamus Besar Bahasa Indonesia app, these comments reflect a variety of opinions, making it important to identify sentiment in order to understand user feedback. This study processed 2,319 reviews from the Google Play Store through a series of text preprocessing steps such as data cleaning, tokenization, stop-word removal, stemming, and text reconstruction. Subsequently, the text was converted into a numerical representation using Term Frequency–Inverse Document Frequency (TF-IDF) and classified using the Naïve Bayes algorithm. Testing showed an accuracy of 87.5%. However, the model performed better on positive reviews, with precision, recall, and F1-score values of 0.95, 0.91, and 0.93, respectively, compared with 0.35, 0.46, and 0.40 for negative reviews. This difference indicates that the model was less effective in identifying negative sentiment, potentially due to the dominance of positive reviews in the dataset. These findings suggest that the proposed approach can be used to map user sentiment, although its performance in classifying negative reviews requires further improvement. ]]>
Copyrights © 2024
