Educational Data Mining and CSCL

Learning to collaborate is important. But how does one learn to collaborate face-to-face? What are the actions and strategies to follow for a group of students who start a task? We have analysed aspects of students’ collaboration when working around a multi-touch tabletop enriched with sensors for identifying users, and also at other multi-display settings.

This project sought out to automatically  distinguish, discover and distil salient common patterns of interaction within groups, by mining the logs of students’ tabletop touches and detected speech.


Multiple data mining techniques were used, including: classification, sequence pattern mining, process mining and clustering techniques.


Some key publications:

Martinez-Maldonado, R., Dimitriadis, Y., Martinez-Mones, A., Kay, J. and Yacef, K. (2013). Capturing and analysing verbal and physical collaborative learning interactions at an enriched interactive tabletopInternational Journal on Computer-Supported Collaborative Learning, ijCSCL, 8(4)455-485.

Martinez-Maldonado, R., Yacef, K. and Kay, J. (2013) Data Mining in the Classroom: Discovering Groups’ Strategies at a Multi-tabletop Environment. International Conference on Educational Data mining, EDM 2013, pages 121-128.

Martinez-Maldonado, R., Wallace, J., Kay, J., and Yacef, K. (2011) Modelling and identifying collaborative situations in a collocated multi-display groupware setting.  International Conference on Artificial Intelligence in Education, AIED 2011, pages 196-204.

Martinez-Maldonado, R., Yacef, K., Kay, J., Kharrufa, A., and Al-Qaraghuli, A. (2011) Analysing frequent sequential patterns of collaborative learning activity around an interactive tabletop4th International Conference on Educational Data Mining, EDM2011, pages 111-120, 2011. (Best Student Paper Award, Google Publication Prize 2011).

Leave a Reply

Your email address will not be published. Required fields are marked *