Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{174247,
        author = {Balineni Akhila and A.Anitha Varshini and K.Athmanathan and V.Dhanakoti},
        title = {ENHANCED SENTIMENT ANALYSIS OF APP REVIEWS USING NAIVE BAYES AND ENSEMBLE LEARNING},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {11},
        number = {10},
        pages = {4206-4210},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=174247},
        abstract = {Sentiment analysis is essential for understanding user opinions and enhancing decision-making across industries. This project develops a sentiment classification system using Naïve Bayes algorithms—Multinomial Naïve Bayes (MNB), Bernoulli Naïve Bayes (BNB), Complement Naïve Bayes (CNB), and an Ensemble Voting Classifier—to analyze Google Play Store app reviews. The system efficiently classifies reviews into positive or negative sentiments through extensive text preprocessing, including stopword removal, special character filtering, and TF-IDF vectorization for improved feature extraction. The preprocessed data is used to train and test Naïve Bayes models, with performance evaluated using accuracy, confusion matrices, precision-recall curves, and ROC-AUC scores. Among the models, ComplementNB outperforms others with an AUC of 0.92, demonstrating a strong balance between precision and recall, whereas BernoulliNB struggles due to a high false negative rate. To enhance usability, a Flask-based web application is integrated, allowing users to input reviews and visualize classification results in real time. The study underscores the effectiveness of Bayesian machine learning models for sentiment analysis, demonstrating their scalability and reliability in text classification tasks. The proposed system provides a practical and efficient solution for sentiment analysis in app reviews, aiding businesses in decision-making and user experience improvements.},
        keywords = {Sentiment Analysis, Machine Learning, ComplementNB, BenouliNB, AUC Score, TF-IDF Vectorization.},
        month = {March},
        }