Retrieval-augmented generation analysis of user reviews in Saudi mobile banking apps: a comparative user experience study of iOS and Android
Abstract
Mobile banking in Saudi Arabia has experienced rapid growth driven by the government’s digital transformation efforts under Saudi Vision 2030, which has prompted the adoption of innovative technologies to improve service delivery across digital financial transformation. Analyzing user reviews is instrumental in gauging the success of mobile banking applications (apps). Utilizing sentiment analysis allows banking providers to convert customer feedback into actionable insights, which can help improve their services, attract new customers, and retain current customers. In this study, we conducted a comparative sentiment analysis of mobile banking apps in Saudi Arabia across iOS and Android platforms. We systematically analyzed 15,459 iOS and 230,734 Android user reviews in multiple languages from 10 leading Saudi banks. Utilizing a pre-trained sentiment model, we classified user sentiments into three categories: positive, negative, and neutral. To deepen the evaluation, Retrieval-Augmented Generation (RAG) with GPT-4o was applied to extract fine-grained user concerns, which were visualized through heatmaps of the most frequent usability issues. Our findings revealed clear differences in user satisfaction across mobile banking apps on iOS and Android. On Android, Alrajhi showed the strongest positive sentiment. Both Banque Saudi Fransi and Saudi Investment Bank received consistently negative reviews on iOS and Android. Arab National Bank received strong positive sentiment on iOS…
Read the paper
Related studies
- Knowledge Management Perspective of Generative Artificial Intelligence
- Navigating Generative Artificial Intelligence Promises and Perils for Knowledge and Creative Work
- Characterizing the evolving research on enterprise content management
- Large language models and multimodal foundation models for precision oncology
- From Generative AI to Extended Reality: Multidisciplinary Perspectives on the Challenges, Opportunities, and Future of Educational Computing
- Generative Artificial Intelligence: A New Engine for Advancing Environmental Science and Engineering
Go deeper in Evidence Hub
Evidence Hub adds a study data sheet (design, sample size, evidence level, key numbers), an AI summary and a chat grounded in the paper's text.