Detection of division of labor in multiparty collaboration

Authors:
Noriko Suzuki;Tosirou Kamiya;Ichiro Umata;Sadanori Ito;Shoichiro Iwasawa;Mamiko Sakata;Katsunori Shimohara
Affiliations:
JSPS/Doshisha University, Japan;Kyoto University, Japan;National Institute of Information and Communications Technology, Japan;National Institute of Information and Communications Technology, Japan;National Institute of Information and Communications Technology, Japan;Doshisha University, Kyotanabe, Kyoto, Japan;Doshisha University, Kyotanabe, Kyoto, Japan
Venue:
HCI'13 Proceedings of the 15th international conference on Human Interface and the Management of Information: information and interaction for learning, culture, collaboration and business - Volume Part III
Year:
2013

Citing 5
Cited 0

Quantifying interpersonal influence in face-to-face conversations based on visual attention patterns

CHI '06 Extended Abstracts on Human Factors in Computing Systems
Predicting two facets of social verticality in meetings from five-minute time slices and nonverbal cues

ICMI '08 Proceedings of the 10th international conference on Multimodal interfaces
Analysis environment of conversational structure with nonverbal multimodal data

International Conference on Multimodal Interfaces and the Workshop on Machine Learning for Multimodal Interaction
Dominance detection in meetings using easily obtainable features

MLMI'05 Proceedings of the Second international conference on Machine Learning for Multimodal Interaction
Analyzing the structure of the emergent division of labor in multiparty collaboration

Proceedings of the ACM 2012 conference on Computer Supported Cooperative Work

Quantified Score

Hi-index	0.00

Visualization

Abstract

In the research field of human-computer interaction, there are many approaches to predicting interactive roles, e.g., conversational dominance or active participation. Although interactive roles have been predicted for entire tasks, little attention has been given to evaluating how such roles are reorganized during a task. This paper explains how to construct a model for predicting emergent division of labor and the reorganization of labor in multiparty collaboration using verbal and nonverbal cues. To build the model, we adopted stepwise multiple-regression analysis, which is a type of statistical model analysis, using both behavioral data and third-party evaluations. We confirmed useful verbal and non-verbal parameters for predicting interactive roles and their reorganization through this model.