In an exciting new paper from the Health Simulation Analytics project, we document our approach to give meaning to multimodal group activity data, in order to give personalised feedback to teams as quickly as possible.
Inspired by the metaphor of social translucence, we are proposing a vision to make evidence of collaboration translucent. In doing so, we emphasise that besides the obvious social dimension, collaboration also involves epistemic (the task at hand), physical (the use of tools, devices and the space) and affective (emotions/feelings) dimensions. This way of seeing learning activity is influenced by Dr. Martinez-Maldonado collaborations with Prof. Peter Goodyear who proposed the ACAD framework (see informative video here).
We build on the notion of quantitative ethnography to give meaning to sensor data based on knowledge that can help explain such data (e.g. domain knowledge, theory) in a specific context. We illustrate our approach in the context of simulation in nursing. Simulated scenarios are representative of situations in which it is critical for team members to reflect upon evidence on different aspects of their activity.
We use extracts from our research on collaborative work in two authentic settings: an immersive simulation room (Figure 1, left) and a simulated hospital ward-classroom (right). In these, we capture rich multimodal data, including nurses’ localisation, movement, physiological signals, actions, voice and video. We illustrate how ideas from quantitative ethnography can help reveal important aspects of collaboration, from low level logs, to meaningful higher order constructs. We present four analytics prototypes as exemplar ‘proxies’ for collaboration. We analyse how three of these can play a key role as proxies in terms of social dynamics; embodied strategies; and emotional arousal. We also show the design and deployment of a fourth proxy of group actions shown to actual workgroups after authentic in-the-wild classroom sessions.
This ‘Team Timeline’ can be generated almost instantaneously for the teams to debrief, and reflect on what went well, and what could have been improved:
Echeverria, V., Martinez-Maldonado, R. and Buckingham Shum, S. (2019). Towards Collaboration Translucence: Giving Meaning to Multimodal Group Data. In Proceedings of ACM CHI Conference (CHI’19). ACM, New York, NY, USA, Paper 39, 16 pages. https://doi.org/10.1145/3290605.3300269 [Reprint]
The ACM CHI Conference on Human Factors in Computing Systems is the premier international conference in Computer-Human Interaction (CORE A*), where researchers and practitioners gather from across the world to discuss advances in theory, design and technology.
This presentation summarises and extends the CHI paper: