Case-Based Decision Support with Emotional Feedback Loops: Integrating Human Affective States into Prototype Retrieval

While Barile et al. (2024) explore emotion detection in human-computer interaction (HCI), most CBDS systems, including those in Marling et al. (2008) and Shved et al. (2024), ignore the user’s emotional context when retrieving or ranking cases. This idea proposes a system where facial emotion recognition (using SVMs or deep learning) observes the emotional state of a decision-maker (e.g., frustration, confusion, confidence) as they interact with prototype retrieval. The system then adapts its retrieval strategy: for instance, if frustration is detected, it might prioritize more explainable, simpler, or diverse cases rather than highly technical or similar ones. This dynamic, affect-aware retrieval loop is a novel synthesis of HCI, cognitive science, and case-based reasoning, and could lead to systems that are not only technically accurate but also emotionally supportive—potentially increasing user trust, satisfaction, and decision quality. No prior work directly links affective feedback to prototype retrieval strategies, making this a fresh and promising avenue.

References:

1. Case-Based Decision Support for Patients with Type 1 Diabetes on Insulin Pump Therapy. C. Marling, J. Shubrook, F. Schwartz (2008). European Conference on Case-Based Reasoning.
2. INTELLECTUAL SUPPORT OF THE PROCESSES OF SEARCHING AND EXTRACTION OF PRECEDENTS IN CASE-BASED REASONING APPROACH. A. Shved, Ye. O. Davydenko, H. V. Horban (2024). Radio Electronics, Computer Science, Control.
3. Support Vector Machines Models for Human Decision-Making Understanding: A Different Perspective On Emotion Detection. Paolo Barile, Ayse Alizada, Clara Bassano (2024). The Human Side of Service Engineering.