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

Metehan Doyran; Arjan Schimmel; Pınar Baki; Kübra Ergin; Batıkan Türkmen; Almıla Akdağ Salah; Sander C.J. Bakkes; Heysem Kaya; Ronald Poppe; Albert Ali Salah

doi:10.1007/s12193-021-00364-0

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

Metehan Doyran^*, Arjan Schimmel, Pınar Baki, Kübra Ergin, Batıkan Türkmen, Almıla Akdağ Salah, Sander C.J. Bakkes, Heysem Kaya, Ronald Poppe, Albert Ali Salah

^*Corresponding author for this work

Methodologie en Organisatie van Design

Research output: Contribution to journal › Article › Scientific › peer-review

13 Citations (Scopus)

99 Downloads (Pure)

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.

Original language	English
Pages (from-to)	373-391
Number of pages	19
Journal	Journal on Multimodal User Interfaces
Volume	15
Issue number	4
DOIs	https://doi.org/10.1007/s12193-021-00364-0
Publication status	Published - 2021

Keywords

Affective computing
Board games
Facial expression analysis
Game experience
Group dynamics
Multimodal interaction
Social interactions

Access to Document

10.1007/s12193-021-00364-0

Doyran2021_Article_MUMBAIMulti-personMultimodalBoFinal published version, 2 MBLicence: CC BY

Cite this

@article{adf88e9787864f3abd846a052ba2761c,

title = "MUMBAI: multi-person, multimodal board game affect and interaction analysis dataset",

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.",

keywords = "Affective computing, Board games, Facial expression analysis, Game experience, Group dynamics, Multimodal interaction, Social interactions",

author = "Metehan Doyran and Arjan Schimmel and Pınar Baki and K{\"u}bra Ergin and Batıkan T{\"u}rkmen and Salah, {Almıla Akdağ} and Bakkes, {Sander C.J.} and Heysem Kaya and Ronald Poppe and Salah, {Albert Ali}",

year = "2021",

doi = "10.1007/s12193-021-00364-0",

language = "English",

volume = "15",

pages = "373--391",

journal = "Journal on Multimodal User Interfaces",

issn = "1783-7677",

publisher = "Springer",

number = "4",

}

TY - JOUR

T1 - MUMBAI

T2 - multi-person, multimodal board game affect and interaction analysis dataset

AU - Doyran, Metehan

AU - Schimmel, Arjan

AU - Baki, Pınar

AU - Ergin, Kübra

AU - Türkmen, Batıkan

AU - Salah, Almıla Akdağ

AU - Bakkes, Sander C.J.

AU - Kaya, Heysem

AU - Poppe, Ronald

AU - Salah, Albert Ali

PY - 2021

Y1 - 2021

N2 - 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.

AB - 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.

KW - Affective computing

KW - Board games

KW - Facial expression analysis

KW - Game experience

KW - Group dynamics

KW - Multimodal interaction

KW - Social interactions

UR - http://www.scopus.com/inward/record.url?scp=85101285681&partnerID=8YFLogxK

U2 - 10.1007/s12193-021-00364-0

DO - 10.1007/s12193-021-00364-0

M3 - Article

AN - SCOPUS:85101285681

SN - 1783-7677

VL - 15

SP - 373

EP - 391

JO - Journal on Multimodal User Interfaces

JF - Journal on Multimodal User Interfaces

IS - 4

ER -

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

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this