Leveraging First Response Time into the Knowledge Tracing Model

The field of educational data mining has been using the Knowledge Tracing model, which only look at the correctness of student first response, for tracking student knowledge. Recently, lots of other features are studied to extend the Knowledge Tracing model to better model student knowledge. The goal of this paper is to analyze whether or not the information of student first response time of a question can be leveraged into Knowledge Tracing model and improve Knowledge Tracing’s prediction accuracy. In our experiments, we used discretized first response time data to predict students’ correctness of the next question, and leveraged the result into a Knowledge Tracing model. Our analysis confirmed the value of student first response time in modeling student knowledge.