Automatic Prediction Of Small Group Performance In Information Sharing Tasks
This work addresses performance prediction for small groups in cooperative tasks, though it appears incremental as it applies an existing modeling approach to a specific domain.
The researchers tackled the problem of predicting small group performance in information sharing tasks by modeling conversational dynamics using Markov jump processes, achieving verification that micro-level interaction patterns like speaking turn rates and balanced participation correlate with better group performance.
In this paper, we describe a novel approach, based on Markov jump processes, to model small group conversational dynamics and to predict small group performance. More precisely, we estimate conversational events such as turn taking, backchannels, turn-transitions at the micro-level (1 minute windows) and then we bridge the micro-level behavior and the macro-level performance. We tested our approach with a cooperative task, the Information Sharing task, and we verified the relevance of micro- level interaction dynamics in determining a good group performance (e.g. higher speaking turns rate and more balanced participation among group members).