Deciphering the Code: Evidence for a Sociometric DNA in Design Thinking Meetings

Research output: Chapter in Book/Report/Conference proceedingConference article in proceedingAcademicpeer-review

Abstract

Despite the increased popularity of virtual teams, in-person teamwork remains the dominant way of working. This paper investigates to what extent social signals can be used to infer the work domain of team meetings. It reveals insights into the complex nature of team dynamics, that are not often quantified in literature, during the design thinking process. This was done by using sociometric badges to measure the social interactions of four teams over a three week development cycle. From these interactions we were able to discriminate different modes in the design thinking process used by the teams, indicating that different design thinking modes have different dynamics. Through supervised learning we could predict the modes of Need Finding, Ideation, and Prototyping with F1 scores of 0.76, 0.71, and 0.60 respectively. These performance scores significantly outperformed random baseline models, corresponding to a doubling of F1 score of predicting the positive class, indicating that the models did indeed succeed in predicting design thinking mode. This indicates that wearable social sensors provide useful information in understanding and identifying design thinking modes. These initial findings will serve as a first step towards the development of automated coaches for design thinking teams.
Original languageEnglish
Title of host publicationHCI International 2020 – Late Breaking Posters. HCII 2020
Subtitle of host publication22nd International Conference, HCII 2020, Copenhagen, Denmark, July 19–24, 2020, Proceedings, Part I
EditorsConstantine Stephanidis, Margherita Antona, Stavroula Ntoa
PublisherSpringer, Cham
Pages 53–61
Number of pages9
Volume1293
ISBN (Electronic)978-3-030-60700-5
ISBN (Print)978-3-030-60699-2
DOIs
Publication statusPublished - 8 Nov 2020

Publication series

SeriesCommunications in Computer and Information Science
Volume1293
ISSN1865-0929

Keywords

  • HCI
  • Social signals
  • Human behaviour analysis
  • predictive modeling
  • field study

Cite this