The Symphony of Team Flow in Virtual Teams. Using Artificial Intelligence for Its Recognition and Promotion

Abstract

More and more teams are collaborating virtually across the globe, and the COVID-19 pandemic has further encouraged the dissemination of virtual teamwork. However, there are challenges for virtual teams – such as reduced informal communication – with implications for team effectiveness. Team flow is a concept with high potential for promoting team effectiveness, however its measurement and promotion are challenging. Traditional team flow measurements rely on self-report questionnaires that require interrupting the team process. Approaches in artificial intelligence, i.e., machine learning, offer methods to identify an algorithm based on behavioral and sensor data that is able to identify team flow and its dynamics over time without interrupting the process. Thus, in this article we present an approach to identify team flow in virtual teams, using machine learning methods. First of all, based on a literature review, we provide a model of team flow characteristics, composed of characteristics that are shared with individual flow and characteristics that are unique for team flow. It is argued that those characteristics that are unique for team flow are represented by the concept of collective communication. Based on that, we present physiological and behavioral correlates of team flow which are suitable – but not limited to – being assessed in virtual teams and which can be used as input data for a machine learning system to assess team flow in real time. Finally, we suggest interventions to support team flow that can be implemented in real time, in virtual environments and controlled by artificial intelligence. This article thus contributes to finding indicators and dynamics of team flow in virtual teams, to stimulate future research and to promote team effectiveness.

Perspectives on group flow: Existing theoretical approaches and the development of the integrative group flow theory.

“…Also, observation methods should be created. In addition, objective measures such as behavior (Gloor et al, 2022), communication (Peifer et al, 2021), or physiological parameters (Czeszumski et al, 2022; Shehata et al, 2021) should be considered as a complement to or external criterion for questionnaires and qualitative observation methods. Subsequently, an experimental paradigm should be developed which allows for testing the propositions by manipulating variables of the structure model of the IGFT.…”

A Scoping Review of Flow Research

“…A clear challenge of future flow research is to differentiate individual flow in social contexts from social flow as a social phenomenon with potentially different qualities than individual flow. A recent suggestion to differentiate flow and team flow was made by Peifer et al (2021) , suggesting that flow and team flow share the central components of individual flow, while team flow-specific components are added. In their studies, van den Hout et al (2018) bridge individual experiences of flow with collective experiences of flow.…”

“…While beyond the scope of this review, for future research, there is a need to find a common definition and operationalization of the flow concept, including a common measure of flow which is used in future research to enhance the comparability of results. The EFRN has started to fulfill this aim by agreeing on a definition of flow (see section “Introduction”), and members of the EFRN have suggested models to aggregate components of flow and team flow (e.g., van den Hout et al, 2018 ; Heutte et al, 2021 ; Peifer and Engeser, 2021 ; Peifer et al, 2021 ). The next steps will be to discuss and agree on models and respective measurements.…”

SenseHunger: Machine Learning Approach to Hunger Detection Using Wearable Sensors

“…It was also observed that the window size of 60 s and the step size of 30 were significant for each classifier. In the past, deep learning-based approaches have shown promising results in a variety of application domains such as biology, medicine, and psychology [ 8 , 12 , 13 , 14 , 15 , 42 , 61 ]. However, they are computationally expensive and also require a large number of training samples [ 62 ] to build successful models compared to traditional approaches using hand-crafted features.…”