MUMBAI

multi-person, multimodal board game affect and interaction analysis dataset

Journal article (2021)

Authors

Metehan Doyran Universiteit Utrecht
Arjan Schimmel Universiteit Utrecht
Pınar Baki Boğaziçi University
Kübra Ergin Sahibinden.com, Istanbul
Batıkan Türkmen Boğaziçi University
A.A. Akdag Salah Boğaziçi University, DesIgning Value in Ecosystems , Universiteit Utrecht
Sander C.J. Bakkes Universiteit Utrecht
Heysem Kaya Universiteit Utrecht
Ronald Poppe Universiteit Utrecht
Albert Ali Salah Universiteit Utrecht
Research Group
DesIgning Value in Ecosystems
Copyright: © 2021 Metehan Doyran, Arjan Schimmel, Pınar Baki, Kübra Ergin, Batıkan Türkmen, A.A. Akdag Salah, Sander C.J. Bakkes, Heysem Kaya, Ronald Poppe, Albert Ali Salah
DOI
help_outline
https://doi.org/10.1007/s12193-021-00364-0
Facial expression analysis Social interactions Game experience Affective computing Board games Group dynamics Multimodal interaction
More Info
expand_more

Published Date

2021

Language

English

Research Group

DesIgning Value in Ecosystems

Abstract

Board games are fertile grounds for the display of social signals, and they provide insights into psychological indicators in multi-person interactions. In this work, we introduce a new dataset collected from four-player board game sessions, recorded via multiple cameras, and containing over 46 hours of visual material. The new MUMBAI dataset is extensively annotated with emotional moments for all game sessions. Additional data comes from personality and game experience questionnaires. Our four-person setup allows the investigation of non-verbal interactions beyond dyadic settings. We present three benchmarks for expression detection and emotion classification and discuss potential research questions for the analysis of social interactions and group dynamics during board games.