GroupAffect-4: A Multimodal Dataset of Four-Person Collaborative Interaction

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Seikavandi, Meisam Jamshidi, Modica, Alice, Obara, Anna, Shaffi, Shan Ahmed, Narcizo, Fabricio Batista, Ignatenko, Tanya, Vucurevich, Ted, Haddad, Karim, Barratt, Daniel, Overholt, Daniel, Boldt, Jesper Bunsow, Burelli, Paolo, Dittberner, Andrew Burke
Format: Preprint
Publié: 2026
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866913146301579264
author Seikavandi, Meisam Jamshidi
Modica, Alice
Obara, Anna
Shaffi, Shan Ahmed
Narcizo, Fabricio Batista
Ignatenko, Tanya
Vucurevich, Ted
Haddad, Karim
Barratt, Daniel
Overholt, Daniel
Boldt, Jesper Bunsow
Burelli, Paolo
Dittberner, Andrew Burke
author_facet Seikavandi, Meisam Jamshidi
Modica, Alice
Obara, Anna
Shaffi, Shan Ahmed
Narcizo, Fabricio Batista
Ignatenko, Tanya
Vucurevich, Ted
Haddad, Karim
Barratt, Daniel
Overholt, Daniel
Boldt, Jesper Bunsow
Burelli, Paolo
Dittberner, Andrew Burke
contents 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 groups as a coupled individual, interpersonal, and group-level process. The required signals (per-participant physiology, eye movement, audio, self-report, task outcomes, and personality) are usually fragmented across separate dataset traditions. We introduce GroupAffect-4, a multimodal corpus of 40 participants in 10 four-person groups, each completing four ecologically varied collaborative tasks spanning information pooling, negotiation, idea generation, and a public-goods game. Each participant is instrumented with a wrist-worn physiology sensor, eye-tracking glasses, and a close-talk microphone; sessions include continuous affect self-reports, post-task questionnaires, task outcomes, and Big-Five personality scores, all time-aligned to a shared clock. The dataset covers over 91% of expected physiology windows and 98% of eye-tracking windows, with strong task validity confirmed by a clear affective manipulation check across the negotiation block. We define fifteen benchmarkable targets spanning three analysis levels -- within-person state, between-person traits, and group dynamics -- and report leave-one-group-out feasibility baselines establishing the dataset's evaluative scope. GroupAffect-4 is released with a BIDS-inspired structure, Croissant metadata, a datasheet, per-session quality reports, and open processing scripts. Code and processing scripts are available at https://github.com/meisamjam/GroupAffect-4; the dataset is publicly archived at https://zenodo.org/records/20037847.
format Preprint
id arxiv_https___arxiv_org_abs_2605_19765
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle GroupAffect-4: A Multimodal Dataset of Four-Person Collaborative Interaction
Seikavandi, Meisam Jamshidi
Modica, Alice
Obara, Anna
Shaffi, Shan Ahmed
Narcizo, Fabricio Batista
Ignatenko, Tanya
Vucurevich, Ted
Haddad, Karim
Barratt, Daniel
Overholt, Daniel
Boldt, Jesper Bunsow
Burelli, Paolo
Dittberner, Andrew Burke
Artificial Intelligence
Databases
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 groups as a coupled individual, interpersonal, and group-level process. The required signals (per-participant physiology, eye movement, audio, self-report, task outcomes, and personality) are usually fragmented across separate dataset traditions. We introduce GroupAffect-4, a multimodal corpus of 40 participants in 10 four-person groups, each completing four ecologically varied collaborative tasks spanning information pooling, negotiation, idea generation, and a public-goods game. Each participant is instrumented with a wrist-worn physiology sensor, eye-tracking glasses, and a close-talk microphone; sessions include continuous affect self-reports, post-task questionnaires, task outcomes, and Big-Five personality scores, all time-aligned to a shared clock. The dataset covers over 91% of expected physiology windows and 98% of eye-tracking windows, with strong task validity confirmed by a clear affective manipulation check across the negotiation block. We define fifteen benchmarkable targets spanning three analysis levels -- within-person state, between-person traits, and group dynamics -- and report leave-one-group-out feasibility baselines establishing the dataset's evaluative scope. GroupAffect-4 is released with a BIDS-inspired structure, Croissant metadata, a datasheet, per-session quality reports, and open processing scripts. Code and processing scripts are available at https://github.com/meisamjam/GroupAffect-4; the dataset is publicly archived at https://zenodo.org/records/20037847.
title GroupAffect-4: A Multimodal Dataset of Four-Person Collaborative Interaction
topic Artificial Intelligence
Databases
url https://arxiv.org/abs/2605.19765