Back to search

Cornell University

Group Affect and Group Cohesion in Human-Agent Teams

Abstract

dc:description.abstract

As artificial intelligent (AI) agents are increasingly integrated into teams, human-agent teams need to learn how to integrate and interact with agents while staying cohesive as a group. We explored a video dataset composed of 65 teams, consisting of humans and an AI agent. The teams collaborated in problem-solving and creativity tasks for three continuous rounds. We used an automated emotion recognition system to measure the correlation between group cohesion and Group Affective Balance (GAB), the group's emotional balance over time, and the correlation between group cohesion and the number of detected smiles of the group members. The results indicate that GAB and group cohesion are positively correlated only during the last round of the study (r = 0.27, p <0.05). The implication understands the relationship between group cohesion and emotions expressed during the interaction in human-agent teams.

Degree

thesis:*
Name thesis:degree_name
M.S., Computer Science
Level thesis:degree_level
Master of Science
Discipline thesis:degree_discipline
Computer Science
Grantor
Cornell University
Year dc:date.issued
2021

Author and committee

dc:creator, dc:contributor.*
Author dc:creator
  • Kim, Se Yun
Chair dc:contributor.chair
  • Jung, Malte F
Committee member dc:contributor.committeemember
  • Fussell, Susan R.

Subjects

dc:subject × 2

Rights

Language dc:language.iso
en

Identifiers

dc:identifier.*
Dc Identifier Bibid
15160303
Dc Identifier Other
ProQuest Submission ID: 11254
ProQuest Publication ID: 28651483

Chain of custody

source
Harvested from
Cornell University
Base URL
ecommons.cornell.edu/server/oai/request
Last updated
2026-11-19
Source record
OAI-PMH GetRecord
citation

Kim, Se Yun. Group Affect and Group Cohesion in Human-Agent Teams. Master of Science thesis, Cornell University, 2021. https://hdl.handle.net/1813/110421