From Momentary Emotion Inference to Sustained Emotion Support: Evaluating a Companion Agent in a Longitudinal Study

📅 2026-09-14
📈 Citations: 0
Influential: 0
📄 PDF
🤖 AI Summary
研究通过14天内与19名参与者使用基于理论的情绪调节伴侣PAIR,评估生成代理在持续情绪支持中的效果,发现指导对话后情绪改善且个性化支持随时间增强。
📝 Abstract
Sustained emotional support is a long-horizon interaction task closely tied to human well-being. Recent research demonstrates generative agents' capacity for momentary emotional support, yet how these capabilities sustain support over time remains unclear. To examine this challenge, we deployed PAIR, a theory-based emotion-regulation companion, with 19 participants for 14 days. Across 1,093 sessions, we paired emotion estimates with self-reports before and after guidance and analyzed logs and interviews. Estimates corresponded more closely to self-reported valence and dominance than arousal. Guided conversations were followed by higher valence and state-dependent arousal changes. Participants felt understood through contextual exploration and emotional acknowledgment, acting on guidance suited to their needs and constraints. Perceived helpfulness of guided conversation significantly increased over time. Our findings link memory updates and retained corrections to cross-session personalization, informing future emotional support tools that adapt to evolving needs, learn from prior outcomes, and preserve user control over memory.
Problem

Research questions and friction points this paper is trying to address.

Sustained emotional support
Generative agents
Longitudinal study
Emotion regulation
Innovation

Methods, ideas, or system contributions that make the work stand out.

sustained emotional support
personalization
emotion-regulation companion
longitudinal study
memory updates
🔎 Similar Papers
💼 Related Jobs
No related jobs found.
K
Kexin Quan
School of Information Sciences, University of Illinois Urbana-Champaign, United States
Zijian Ding
Zijian Ding
University of California, Los Angeles
electronic design automation
J
Jiaye Yong
University of Illinois Urbana-Champaign, United States
Q
Qinshi Zhang
Department of Computer Science, Florida State University, United States
Dong Wang
Dong Wang
Professor at University of Illinois Urbana-Champaign
Social SensingHuman-centered AISocial IntelligenceAI for Social GoodAI for Science
Jessie Chin
Jessie Chin
University of Illinois Urbana-Champaign
conversational agentsinformation searchhealth literacyaging and human-computer interactionlearning