mlsanityData to 14 Oct 2026

Empath: Tracing Multi-Level Emotion Dynamics in Crisis Counseling Dialogues

arXiv 2609.29056 ↗First posted 24 Sep 2026cs.CL cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Emotion dynamics are critical for understanding crisis-support conversations, yet most computational work treats emotion as static utterance-level labels. We introduce EMPATH, a framework for understanding affective dynamics in mental health dialogues across three granularities: turn-level labels, transition probabilities, and global conversation archetypes. Applying EMPATH to text-based crisis conversations with self-identified Black texters discussing grief, we find persistent negative affect, gradual hope-ward transitions, distinct texter-volunteer emotional roles, and heterogeneous recovery trajectories. These results highlight the informative patterns that emerge from computationally understanding crisis support and expressions of grief as dynamic processes within conversations, as well as the overall value of emotion-dynamic analysis for analyzing and comparing affect in dialogues.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 19 of its 44 references that are in the map. First posted on arXiv 24 Sep 2026.

Builds on

19 of 44 references.

References · 19

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2024The Llama 3 Herd of Modelscited by 14,715
  3. 2018e-SNLI: Natural Language Inference with Natural Language Explanationscited by 468
  4. 2021Towards Emotional Support Dialog Systemscited by 299
  5. 2016Demographic Dialectal Variation in Social Media: A Case Study of African-American Englishcited by 196
  6. 2024Roleplay-doh: Enabling Domain-Experts to Create LLM-simulated Patients via Eliciting and Adhering to Principlescited by 73
  7. 2023Mental-LLM: Leveraging Large Language Models for Mental Health Prediction via Online Text Datacited by 66
  8. 2023Harnessing large-language models to generate private synthetic textcited by 65
  9. 2023Evaluation of African American Language Bias in Natural Language Generationcited by 36
  10. 2023Multimodal Multi-loss Fusion Network for Sentiment Analysiscited by 27
  11. 2025When Can We Trust LLMs in Mental Health? Large-Scale Benchmarks for Reliable LLM Evaluationcited by 19
  12. 2024Differentially Private Knowledge Distillation via Synthetic Text Generationcited by 18
7 more
  1. 2025Can LLM-Simulated Practice and Feedback Upskill Human Counselors? A Randomized Study with 90+ Novice Counselorscited by 13
  2. 2025Multimodal Emotion Recognition in Conversations: A Survey of Methods, Trends, Challenges and Prospectscited by 11
  3. 2025IntentionESC: An Intention-Centered Framework for Enhancing Emotional Support in Dialogue Systemscited by 11
  4. 2024EmoDynamiX: Emotional Support Dialogue Strategy Prediction by Modelling MiXed Emotions and Discourse Dynamicscited by 9
  5. 2025Counterfactual Simulatability of LLM Explanations for Generation Taskscited by 8
  6. 2025A Review of Incorporating Psychological Theories in LLMscited by 6
  7. 2025Emotional Supporters often Use Multiple Strategies in a Single Turncited by 5

Built on by

Not cited yet.