"Emotional Intelligence in Conversational AI: A Sentiment-Aware Framework for E-Commerce Growth".
Abstract
As AI becomes a central interface for online commerce, a key limitation remains: machines struggle to understand human emotion. This empathy gap often leads to frustrated users and reduced satisfaction. This study develops a sentiment-aware chatbot framework combining the speed of VADER with the contextual understanding of BERT. By interpreting the emotional tone of user input, the chatbot adapts its responses dynamically, creating more human-like interactions. Applied to a sustainable e-commerce platform, the proposed system demonstrated measurable improvements in customer retention and Net Promoter Scores, while reducing emotional stress on support agents. These results highlight the potential of emotionally intelligent AI in building trust and loyalty.
Fields of Study & Subjects
AI in Service Interactions
Emotion and Mood Recognition
Recommender Systems and Techniques
Publication details
- Journal / source
- Zenodo (CERN European Organization for Nuclear Research)
- Publication date
- 3 January 2026
- Language
- EN
- Document type
- Preprint