A Topic Modeling Approach to Study the Impact of Manager Interventions on Design Team Cognition

2021 ◽  
Author(s):  
Jonathan Cagan ◽  
JOSHUA GYORY ◽  
Kenneth Kotovsky
Author(s):  
Joshua T. Gyory ◽  
Kenneth Kotovsky ◽  
Jonathan Cagan

Abstract In order to computationally study design cognition under design process management, this work utilizes a topic modeling approach to analyze design team discourse during problem-solving. The particular experimental design, from previous work by the authors, places one of the design team conditions under the guidance of a human process manager. In that work, teams under this guidance outperformed the unmanaged teams in terms of their design solutions. This opens the opportunity to not only model design discourse during problem solving, but also explore the impact of process manager interventions and their impact on design cognition. Utilizing this approach, a topic model is trained on discourse of human designers, for both managed and unmanaged teams, collaboratively solving a design problem. Results show that the two team conditions significantly differ in a number of the extracted topics, and in particular, those topics that most pertain to the manager interventions. Furthermore, a before and after analysis of the topic-motivated interventions, reveals that the process manager interventions significantly shift the topic mixture of the team members’ discourse toward that of the interventions immediately after they are provided. Together, these results not only corroborate the effect of the process manager interventions on design team discourse and cognition, but provide promise in the computational detection and facilitation of design interventions based on real-time discourse data.


2020 ◽  
Author(s):  
Celia C. Lo ◽  
Young S. Kim ◽  
Thomas Allen ◽  
Andrea Allen ◽  
P. Allison Minugh ◽  
...  

Author(s):  
Beth Lyall-Wilson ◽  
Nicolas Kim ◽  
Elizabeth Hohman

This paper describes the development and new application of a text modeling process for identifying human factors topics, such as fatigue, workload, and distraction in aviation safety reports. Current approaches to identifying human factors topic representations in text data rely on manual review from subject matter experts. The implementation of a semi-supervised text modeling method overcomes the need for lengthy manual review through an initial extraction of pre-defined human factors topics, freeing time for focus on analyzing the information. This modeling approach allows analysts to use keywords to define topics of interest up front and influence the convergence of the model toward a result that reflects them, which provides an advantage over classic topic modeling approaches where domain knowledge is not integrated into the generation of derived topics. This paper includes a description of the modeling approach and rationale, data used, evaluation methods, challenges, and suggestions for future applications.


2020 ◽  
Vol 10 ◽  
Author(s):  
Raffaele Sperandeo ◽  
Giovanni Messina ◽  
Daniela Iennaco ◽  
Francesco Sessa ◽  
Vincenzo Russo ◽  
...  

2021 ◽  
Vol 38 (3) ◽  
pp. 415-428
Author(s):  
Florian Simon ◽  
Elodie Gautier-Veyret ◽  
Aurélie Truffot ◽  
Marylore Chenel ◽  
Léa Payen ◽  
...  
Keyword(s):  

Author(s):  
Mirco Pistelli ◽  
Valentina Natalucci ◽  
Lucia Bastianelli ◽  
Laura Scortichini ◽  
Veronica Agostinelli ◽  
...  

Sign in / Sign up

Export Citation Format

Share Document