Knowledge tracing (KT) is a research topic that seeks to model the knowledge acquisition of students by analyzing their past performance in answering questions, based on which their performance in answering future questions is predicted. Each question involves a knowledge component (KC) such as the topics concerned or the skills required. However, existing models only consider whether a student answers a question correctly at the end, but not the process of how the student attempts to answer it. It is anticipated that the interaction process can at least partially reveal the thinking process of the student, and hopefully even the competence of acquiring or understanding each of the KCs. By analyzing fine-grained clickstream events recorded for each question, we can better unde...[ Read more ]

Knowledge tracing (KT) is a research topic that seeks to model the knowledge acquisition of students by analyzing their past performance in answering questions, based on which their performance in answering future questions is predicted. Each question involves a knowledge component (KC) such as the topics concerned or the skills required. However, existing models only consider whether a student answers a question correctly at the end, but not the process of how the student attempts to answer it. It is anticipated that the interaction process can at least partially reveal the thinking process of the student, and hopefully even the competence of acquiring or understanding each of the KCs. By analyzing fine-grained clickstream events recorded for each question, we can better understand the student’s ability and performance or even the learning process, just like a personal tutor observing how a student solves a problem.

Based on real student interaction data including clickstream events collected from an online learning platform on which students solve mathematics problems, we conduct clustering analysis for each question to show that clickstreams can reflect students’ behavior such as the steps and order of answering a question, time allocation, and score acquiring ability. We then propose the first clickstream-based KT model, dubbed the Click-stream Knowledge Tracing (CKT) model, which augments a basic KT model by modeling the clickstream activities of students when answering questions. We apply different variants of CKT and compare them with the baseline KT model that does not use clickstream data. Despite the limited number of questions with clickstream data and its noisy nature, which may compromise the data quality, we show that incorporating clickstream data leads to performance improvement. This pilot study will likely open a new direction in KT research by analyzing the finer-grained interaction data of students on online learning platforms.