Sentiment Analysis of Getcontact Application Reviews on Google Play Store Using Naive Bayes Algorithm

Abstract

In the contemporary digital era, the increasing incidence of fraud and unwanted communications has become a serious concern, driving the adoption of security apps like GetContact. This study aims to analyze public perception of the GetContact app by conducting a systematic sentiment analysis of user reviews on the Google Play Store. Using a text mining framework, 990 user reviews were collected, processed to ensure data quality, and then classified using the Naive Bayes algorithm to determine sentiment polarity. Quantitative results show a significant dominance of negative sentiment, comprising 419 reviews (42.3%), followed by positive sentiment, comprising 291 reviews (29.4%), and neutral sentiment, comprising 280 reviews (28.3%). Qualitative analysis through data visualization reveals that the primary user complaints center on basic functionality issues such as login difficulties, while positive sentiment is driven by the perception that the app is very helpful. These findings provide critical actionable insights for developers to prioritize improvements in areas of greatest user concern. This study advances sentiment analysis by demonstrating the efficacy of Naive Bayes in classifying unstructured app reviews, offering a scalable approach to evaluating user feedback in mobile app development.