GroupAffect-4: A Multimodal Dataset of Four-Person Collaborative Interaction
The GroupAffect-4 dataset introduces a multimodal approach to studying four-person collaborative interactions. It includes data from 40 participants engaged in various tasks, capturing physiological, audio, and self-reported affective signals. This dataset aims to enhance the analysis of interpersonal and group-level dynamics in collaborative settings.
- ▪GroupAffect-4 consists of 40 participants divided into 10 four-person groups.
- ▪Participants completed four different collaborative tasks while being monitored with various sensors.
- ▪The dataset provides comprehensive data, including physiological signals, eye-tracking, and personality assessments.
Opening excerpt (first ~120 words) tap to expand
Computer Science > Artificial Intelligence arXiv:2605.19765 (cs) [Submitted on 19 May 2026] Title:GroupAffect-4: A Multimodal Dataset of Four-Person Collaborative Interaction Authors:Meisam Jamshidi Seikavandi, Alice Modica, Anna Obara, Shan Ahmed Shaffi, Fabricio Batista Narcizo, Tanya Ignatenko, Ted Vucurevich, Karim Haddad, Daniel Barratt, Daniel Overholt, Jesper Bunsow Boldt, Paolo Burelli, Andrew Burke Dittberner View a PDF of the paper titled GroupAffect-4: A Multimodal Dataset of Four-Person Collaborative Interaction, by Meisam Jamshidi Seikavandi and 12 other authors View PDF HTML (experimental) Abstract:Existing affective-computing, social-signal-processing, and meeting corpora capture important parts of human interaction, but they rarely support analysis of affect in co-located…
Excerpt limited to ~120 words for fair-use compliance. The full article is at arXiv cs.AI.
Discussion
0 commentsMore from arXiv cs.AI
