Incorporating Scafolding and Tutor Context into Bayesian Knowledge Tracing to Predict Inquiry Skill Acquisition

Type: Evidence | Proposition: B: Teaching | Polarity: | Sector: | Country:

In this paper, we incorporate scaffolding and change of tutor context within the Bayesian Knowledge Tracing (BKT) framework to track students’ developing inquiry skills. These skills are demonstrated as students experiment within interactive simulations for two science topics. Our aim is twofold. First, we desire to improve the models’ predictive performance by adding these factors. Second, we aim to interpret these extended models to reveal if our scaffolding approach is effective, and if inquiry skills transfer across the topics. We found that incorporating scaffolding yielded better predictions of individual students’ performance over the classic BKT model. By interpreting our models, we found that scaffolding appears to be effective at helping students acquire these skills, and that the skills transfer
across topics.

This paper reports research using Bayesian Knowledge Tracing to predict student performance in inquiry process skills across science topics (particularly data collection).  The main focus is on the accuracy of the prediction but they also use it to evaluate the effectiveness of scaffolding offered.  This could be used positive evidence for the LACE hypothesis B – improving teaching.


Citation: Sao Pedro, M., Baker, R.S.J.D. and Gobert, J, Incorporating Scaffolding and Tutor Context into Bayesian Knowledge Tracing to Predict Inquiry Skill Acquisition, S. D'Mello, R. Calvo, & A. Olney (Eds.). Proc Educational Data Mining (EDM) 2013 | Url: