LEVERAGING GENERATIVE AI FOR EFFICIENT MOBILE APP FEEDBACK CLASSIFICATION AND QUALITY IMPROVEMENT

Abstract

This paper introduces an innovative approach to mobile app user feedback analysis by harnessing the power of Generative AI technologies. We present an integrated system architecture that seamlessly combines an API-based scheduler for comprehensive data collection, a cutting-edge Generative AI classifier for nuanced feedback categorization, robust database integration for efficient data management, and an interactive visualization module for actionable insights. Our system goes beyond traditional classification methods by not only categorizing feedback based on predefined themes but also dynamically generating new themes for previously unclassified feedback. This adaptive approach ensures comprehensive coverage of user concerns while maintaining a structured classification system. We evaluate our method using a diverse and extensive dataset of feedback items collected from multiple sources, including app store reviews, in-app feedback, customer care logs, and direct user emails. The experimental results demonstrate the significant advantages of our GenAI classifier over conventional approaches in terms of accuracy, theme coverage, and scalability. This paper illustrates a substantial contribution to the field of AI-driven feedback analysis, illustrating the transformative potential of Generative AI in enhancing mobile app quality and user experience through more efficient, accurate, and adaptable feedback processing methodologies