The Effect of Automatic Reassessment and Relearning on Assessing Student Long-Term Knowledge in Mathematics

Yutao Wang, Neil T. Heffernan

Intelligent Tutoring Systems (ITS) give assessments to estimate a student’s current knowledge. A great deal of work in the past years, (e.g. KDD Cup2010) has focused on predict students immediate next performance, while what is important is will the student retain that knowledge for later use. Some previous studies such as Wang, et al, Xiong, et al. have started to investigate this question by trying to predict student retention after a time interval of several days. We created a novel system that would automatically reassess and allow students to relearn the material to enhance a student’s long-term knowledge. It is showed before that this intervention raised student learning, and now we are wondering if it also makes assessment of student long-term knowledge better (i.e, more predictive power). The result shows that the reassessment and relearning information is very useful in assessing student long-term knowledge.

The final publication is available at Springer via