This study investigates how emotional intelligence and AI techniques can classify user-reported issues in retail mobile banking apps and examine the associations between emotions and problem reporting. Using over 216,000 user reviews from the Bank of America Mobile Banking App, we extract sentiment and eight emotional dimensions via the NRC Emotion Lexicon. K-Means clustering identifies key service-related issues, while machine learning and deep learning models (e.g., MLP, CNN, RNN) predict problem types with over 93% accuracy. Regression analysis shows that negative sentiment is strongly associated with problem reporting, while emotions like trust and anger are linked to lower reporting likelihood. Our findings highlight the role of emotion in digital user engagement and offer practical insights for designing emotionally intelligent banking services. This is the first study to combine emotional intelligence and AI to classify user issues and assess how emotional cues relate to reporting behavior in retail mobile banking. By integrating psychological theories of emotional intelligence with computational modeling, this study advances our understanding of affective behavior in digital financial environments. The findings contribute to the broader field of psychology by demonstrating how emotional cues are associated with user cognition, trust, and decision-making in technology-mediated interactions.
LI et al. (Mon,) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: