Evaluation of student collaboration on canvas LMS using educational data mining techniques

Online discussion forums provide valuable information about students' learning and engagement in course activities. The hidden knowledge in the contents of these discussion posts can be examined by analyzing the social interactions between the participants. This research investigates students' learning and collaborative problem-solving aspects by applying social network analysis (SNA) metrics and sophisticated computational techniques. The data is collected from online course discussion forums on Canvas, a Learning Management System (LMS), in a CS1 course at a medium-sized US University. The research demonstrates that efficient tools are needed to model and evaluate goal-oriented discussion forums constructed from active student collaborations. This research aims to develop a systematic data collection and analysis instrument incorporated into LMSs that enables grading the discussions to improve instructional outcomes, gain insights into and explain educational phenomena. The study also emphasizes important SNA metrics that analyze students' social behavior since a positive correlation was seen between the number of posts made by students and their academic performance in terms of the final grade. The prototype developed (CODA - Canvas Online Discussion Analyzer) helps evaluate students' performance based on the useful knowledge they share while participating in course discussions. The experimental results provided evidence that analysis of structured discussion data offers potential insights about changes in student collaboration patterns over time and students' sense of belongingness for pedagogical benefits. As future work, further analysis will be done by extracting additional students' data, such as their demographic data, majors, and performance in other courses to study cognitive and behavioral aspects from the collaboration networks.