D’Angelo, C., Smith, J., Alozie, N., Tsiartas, A., Richey, C., & Bratt, H. (2019). Mapping Individual to Group Level Collaboration Indicators Using Speech Data. In Lund, K., Niccolai, G. P., Lavoué, E., Hmelo-Silver, C., Gweon, G., & Baker, M. (Eds.), A Wide Lens: Combining Embodied, Enactive, Extended, and Embedded Learning in Collaborative Settings, 13th International Conference on Computer Supported Collaborative Learning (CSCL) 2019, Volume 2 (pp. 628-631). Lyon, France: International Society of the Learning Sciences.
Automatic detection of collaboration quality from the students’ speech could support teachers in monitoring group dynamics, diagnosing issues, and developing pedagogical intervention plans. To address the challenge of mapping characteristics of individuals’ speech to information about the group, we coded behavioral and learning-related indicators of collaboration at the individual level. In this work, we investigate the feasibility of predicting the quality of collaboration among a group of students working together to solve a math problem from human-labelled collaboration indicators. We use a corpus of 6th, 7th, and 8th grade students working in groups of three to solve math problems collaboratively. Researchers labelled both the group-level collaboration quality during each problem and the student-level collaboration indicators. Results using random forests reveal that the individual indicators of collaboration aid in the prediction of group collaboration quality.