Cluster Analysis of Data Logs Generated by Intelligent Tutor to Determine Students' Learning Profiles

Student's Patterns of Interaction with a Mathematics Intelligent Tutor: Learning Analytics Application

“…During initial exploratory investigation, it was found that students with a high value for the variable mtop chose their topics sequentially [11]. In the next stage of analysis, data logs of two students were examined.…”

“…This analysis can reveal detailed information about different patterns of learning activities, such as the rate at which learner is progressing in the learning environment, under which circumstances their progress is accelerated or decelerated. Cluster analysis, decision trees, artificial neural networks and support vector machines are some examples of techniques used for analysis of such vast amount of data [11]. Cluster analysis involves statistical methods which are commonly used for grouping cases which exhibit similar patterns of learning activities.…”

“…If {a} is a conceptual unit in the list of topics mastered and {b} is another conceptual unit not in that list, then the path from {a} to {b} isfeasible if the conceptual unit a is a pre-requisite of the conceptual unit b. The set of all such units like the unit b, form a set of units that the student is ready to learn [11,14].…”