Analysis of Google Play Store User Sentiment Towards Application X Using the SVM Algorithm

This study uses the Support Vector Machine (SVM) algorithm to examine user opinions about the X app on the Google Play Store. Data went through preprocessing steps like cleaning, casefolding, tokenizing, filtering, and sentence reconstruction from 5,000 reviews that were gathered via web scraping. Using a lexicon-based method, sentiment labeling was carried out, categorizing reviews into three groups: neutral, negative, and positive. The findings indicated that 49.4% of respondents had unfavorable opinion, followed by neutral (29.8%) and positive (20.8%). An SVM model with an accuracy of 86.3% was generated by feature extraction using Bag of Words with CountVectorizer. The neutral class had the highest recall (0.96) and the negative class the highest precision (0.95). With an F1-score of 0.78, the positive class performed the worst, most likely as a result of data imbalance. Despite difficulties in categorizing minority classes, this study shows that SVM is useful in sentiment analysis.