Skip to Main content Skip to Navigation
New interface
Journal articles

Social Signals of Cohesion in Multi-party Interactions

Abstract : Group conversation is a frequently used form of communication for exchanging ideas and making decisions. Cohesion is an emergent phenomenon that describes the members' attraction towards the group and towards working together. In this paper, we present the cohesion labels assigned to segments from [redacted], a multimodal dataset of simulated medical consultations. Then, we present the analysis performed to identify social cues that characterize cohesion and report the accuracy for classifying cohesion. Results show that non-verbal social cues like gaze, facial AUs, laughter etc., indeed convey information regarding the level of cohesion. Finally we present a preliminary evaluation conducted using the prominent cues to simulate a cohesive group of agents. CCS CONCEPTS • Human-centered computing → Collaborative and social computing.
Document type :
Journal articles
Complete list of metadata
Contributor : Catherine Pelachaud Connect in order to contact the contributor
Submitted on : Monday, November 15, 2021 - 12:57:34 PM
Last modification on : Sunday, June 26, 2022 - 3:19:36 AM
Long-term archiving on: : Wednesday, February 16, 2022 - 8:31:04 PM


Files produced by the author(s)



Reshmashree B Kantharaju, Catherine Pelachaud. Social Signals of Cohesion in Multi-party Interactions. Proceedings of the 21th ACM International Conference on Intelligent Virtual Agents, 2021, ⟨10.1145/3472306.3478362⟩. ⟨hal-03428888⟩



Record views


Files downloads