Voting classifier in pain points identification

Abstract

A successful app understands and addresses the needs of its users. Pain points-specific difficulties and frustrations that users experience while using an application-are crucial for understanding user expectations and improving user experience. Google Play Store reviews can be a valuable source for identifying these pain points, but this raw data requires processing to be useful for developers. This study develops a model to automatically classify reviews as either containing pain points or not. We chose the voting classifier as our primary algorithm because of its proven ability to produce models with high accuracy through combining the strengths of multiple classifiers. After evaluating 5 different classifier methods, our research shows that the optimal model combines XGradient boosting, multinomial naïve Bayes, and logistic regression-with each contributing unique strengths in text classification. This combination achieves 90% accuracy and a 90% F1-Score, outperforming previous studies that used neural networks (which achieved 80% accuracy). The model successfully identifies user frustrations from app reviews, providing developers with actionable insights to improve their applications.