[Paper Review] Social Analytics of Team Interaction using Dynamic Complexity Heat Maps and Network Visualizations

Travis J. Wiltshire, Dan Hudson+3 more|arXiv (Cornell University)|Sep 7, 2020

Mental Health Research Topics72 references4 citations

TL;DR

This paper proposes a novel social analytics framework that combines Rhythm Badge sensor data with Dynamic Complexity Heat Maps and network visualizations to analyze team interaction dynamics in real time. By applying this method to a Lost at Sea simulation, the authors identify critical transitions in team communication, structural shifts in engagement and energy, and provide actionable visual feedback for improving team performance and cohesion.

ABSTRACT

Given the increasing complexity of many sociotechnical work domains, effective teamwork has become increasingly crucial. While there is evidence that face-to-face communication contributes to effective teamwork, methods for understanding the time-varying nature and structure of team communication are limited. In this work, we combine sensor-based social analytics of Sociometric badges (Rhythm Badge) with two visualization techniques (Dynamic Complexity Heat Maps and Network Visualizations) to advance an intuitive way of understanding the dynamics of team interaction. To demonstrate the utility of our approach, we provide a case study that examines one team's interaction for a Lost at Sea simulation. We were able to recover transitions in the task and team interaction as well as uncover structural changes in team member energy and engagement, which we visualize using networks. Taken together, this work represents an important first step at optimizing team effectiveness by identifying critical transitions/events in team communication and interaction patterns.

Motivation & Objective

• To address the lack of methods for analyzing time-varying, multi-scale team communication in complex sociotechnical work domains.
• To develop an intuitive, data-driven approach for visualizing team interaction dynamics using sensor-based social analytics.
• To identify critical transitions and structural changes in team energy, engagement, and coordination during collaborative problem solving.
• To enable real-time feedback for teams by visualizing communication patterns and individual contributions.
• To lay a foundation for optimizing team effectiveness through objective, visual analytics of team interaction.

Proposed method

• Utilizes Rhythm Badge sensors to capture real-time, multi-modal social interactions, including proximity, speech, and turn-taking.
• Applies Dynamic Complexity Heat Maps to detect critical instabilities and transitions in team interaction patterns over time.
• Constructs energy and engagement networks to visualize the strength and structure of communicative connections between team members.
• Combines sensor data with network visualization techniques to represent temporal changes in team dynamics and coordination.
• Employs a case study approach using a Lost at Sea simulation to validate the method in a controlled, complex team task.
• Uses network analysis to identify shifts in team structure, such as changes in leadership or participation patterns.

Experimental results

Research questions

• RQ1 How can sensor-based social analytics detect critical transitions in team interaction during collaborative problem solving?
• RQ2 What structural changes in team energy and engagement can be visualized using network representations of interaction data?
• RQ3 How do dynamic complexity heat maps reveal instability or coordination shifts in team communication over time?
• RQ4 To what extent can visual feedback from these analytics improve team awareness and performance?
• RQ5 What role do individual engagement and energy levels play in shaping overall team dynamics during complex tasks?

Key findings

• The Dynamic Complexity Heat Maps successfully identified critical transition points in team interaction, such as shifts from discussion to decision-making phases in the Lost at Sea simulation.
• Network visualizations revealed distinct structural changes in team engagement and energy, including shifts in leadership and participation patterns during task progression.
• The method detected that communication coordination patterns evolved over time, with periods of high stability and instability linked to task milestones.
• Individual team members' energy and engagement levels were visually quantified, enabling identification of dominant contributors and potential disengagement.
• The integration of sensor data with visualization techniques provided an intuitive, objective means of assessing team dynamics in real time.
• The approach demonstrated potential for real-time feedback, increasing team awareness of behavioral patterns and fostering accountability.