Evidence of the month: learning-analytics-based prediction models

0

Each month, we highlight one of the new additions to the LACE Evidence Hub, which brings together evidence about learning analytics. You are welcome to add to the Hub site, which you can visit via a tab at the top of this page.

The Evidence of the Month for July 2015 is a paper dealing with the ‘Stability and sensitivity of learning-analytics-based prediction models‘. In May, it won Best Paper award at the 7th International conference on Computer Supported Education.

This paper reports on a study that investigated whether prediction models remain the same when the instructional context is repeated with a new cohort of students, and whether prediction models change when relevant aspects of the instructional context are adapted.

The study found that the value of data about learning dispositions is strongly dependent on the time at which richer (assessment) data become available, and on the need for timely signalling of under performance. If timely feedback is required, the combination of data extracted from e-tutorials (both in practice and test modes) and learning disposition data was found to be the best mix to support learning analytics applications.

These findings can be applied to improve learning and teaching because feedback related to learning dispositions (for example, by flagging suboptimal learning strategies, or inappropriate learning regulation) is generally open to interventions to improve the learning process. The same is true of feedback related to suboptimal use of e-tutorials; it is both predictive and open for intervention.

Citation: Tempelaar, D. T.; Rienties, B. and Giesbers, B. (2015). Stability and sensitivity of Learning Analytics based prediction models. In: Proceedings of 7th International conference on Computer Supported Education (Helfert, Markus ; Restivo, Maria Teresa; Zvacek, Susan and Uho, James eds.), 23-25 May 2015, Lisbon, Portugal, CSEDU, pp. 156–166. | Url: http://oro.open.ac.uk/43446/
Share.

About Author

Rebecca is a lecturer at The Open University in the UK, focused on educational futures, learning analytics, MOOCs, augmented learning and online social learning. She is a member of the steering committee of the Society for Learning Analytics Research (SoLAR) and was Workshops Chair of the second Learning Analytics and Knowledge conference (LAK 2012). She co-chaired the 1st and 2nd International Workshops on Discourse-Centric Learning Analytics, held in Belgium and the US, as well as the first UK SoLAR Flare (a national learning analytics event). Her most recent publication is the book ‘Augmented Education’, published by Palgrave in May 2014. Rebecca is working on the LACE work package relating to learning analytics in higher education.

Leave A Reply