GroupAffect-4 is a new multimodal corpus of four-person collaborative interactions with synchronized physiological, eye-tracking, audio, and affective self-report data from 40 participants across 10 groups and 15 benchmark targets.
Chang, Sungbok Lee, and Shrikanth S
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.AI 2years
2026 2representative citing papers
Multimodal LLM analysis correlates better with TRUST-Pathos than acoustic SER models in a case study of one Bundestag speech, while acoustic features help with arousal.
citing papers explorer
-
GroupAffect-4: A Multimodal Dataset of Four-Person Collaborative Interaction
GroupAffect-4 is a new multimodal corpus of four-person collaborative interactions with synchronized physiological, eye-tracking, audio, and affective self-report data from 40 participants across 10 groups and 15 benchmark targets.
-
Beyond Acoustic Emotion Recognition: Multimodal Pathos Analysis in Political Speech Using LLM-Based and Acoustic Emotion Models
Multimodal LLM analysis correlates better with TRUST-Pathos than acoustic SER models in a case study of one Bundestag speech, while acoustic features help with arousal.