SENTIMENT ANALUSIS ON GOOGLE PLAY STORE DATA USING NLP

Abstract

Sentiment analysis on Google Play Store reviews plays a vital role in understanding user feedback and enhancing app performance. This study applies Natural Language Processing (NLP) and machine learning models—Random Forest, Decision Tree, and Support Vector Machine (SVM)—to classify sentiments as positive, negative, or neutral. User reviews are preprocessed using tokenization, stopword removal, and vectorization. The models are evaluated based on accuracy, precision, recall, and F1-score, with Random Forest offering strong predictive power, Decision Tree providing interpretability, and SVM ensuring high classification accuracy. A comparative analysis highlights the most effective model, emphasizing the value of machine learning in supporting data-driven app development decisions.