Modeling Long-Term Emotional Support Through Causal World Modeling With Imitation Learning
Bibliographic Data
| ID | 22107084 |
|---|---|
| Authors | Mingzheng Li (0000-0001-8444-4044, University of Science and Technology of China), Fei Wang (0000-0003-0860-6317, Hefei University of Technology), Kun Li (0000-0001-5862-1959, United Arab Emirates University), YanYan Wei (0000-0002-8218-1954, Hefei University of Technology), Yiqi Nie (0009-0001-1739-4515, Anhui University), Yanbin Hao (0000-0002-1333-4726, Hefei University of Technology), Xun Yang (0000-0002-2033-3385, University of Science and Technology of China), Meng Wang (0000-0001-5799-549X, Hefei University of Technology) |
| Year | 2026 |
| Volume | 13 |
| Issue | 3 |
| Pages | 3794-3809 |
| Publication date | 2026-06-01 |
| Open Access | Yes |
| Type | ARTICLE |
| Venue | IEEE Transactions on Computational Social Systems (JOURNAL) |
| Journal identifiers | ISSN: 2329-924X • E-ISSN: 2373-7476 |
| Publisher | Institute of Electrical and Electronics Engineers (IEEE) (PUBLISHER) |
| DOI | 10.1109/tcss.2026.3653579 |
| OpenAlex | W7128483899 |
| Language | EN |
| References cited | 55 |
Emotional support conversation systems have emerged as a promising complement to traditional mental health consultations, offering context-aware dialogue to support seekers’ emotional well-being. Despite their potential, two fundamental challenges remain unresolved: 1) modeling long-term emotional trajectory beyond short-term relief; and 2) adapting support strategies to context in a psychologically coherent manner. To address these challenges, we propose CAIWO, a novel framework that integrates world modeling and causality-enhanced imitation learning to systematically support seekers, alleviate psychological stress, and restore emotional balance. Specifically, CAIWO comprises two core components. The first is an emotional world model, which captures long-term emotional trajectories from historical interactions to inform anticipatory guidance. The second is a causality-enhanced imitation learning module, which infers latent causal dependencies to facilitate coherent strategy transitions and mitigate compounding errors typical of conventional imitation learning. By incorporating the final latent variables into the response decoder, CAIWO dynamically adjusts the strategies and generates emotionally resonant responses. Extensive experiments on the ESConv benchmark demonstrate that CAIWO outperforms state-of-the-art baselines by 8.6%, significantly improving the generation of responses that align with seekers’ emotional development and psychological needs
Causal model · Conversation · Imitation · Observational learning · Trajectory · Digital Mental Health Interventions · Emotion and Mood Recognition · Mental Health via Writing
| Highly cited | No |
|---|