A study on student performance evaluation using discussion board networks

Abstract

Node-based social network analysis (SNA) techniques can be used to investigate the significance of actors that play central roles in social networks where the nodes represent people, teams or stakeholders and the links represent the communication, information exchange or collaboration between these nodes (actors). This research investigates how collaborative problem-solving can help in students' learning process. We analyzed the discussion board data collected from online student discussions on Canvas, a Learning Management System (LMS), in a CS1 course of a medium-sized US University. The discussion topics were classified as classroom experiences/ learning, question/answers, opinions, and comments and were used to represent the patterns of interactions in the studentdiscussion networks. Node-based network measures were then applied to unravel the students' interaction patterns to gain insights on students' progress. The textual analysis helped find the most challenging/debated topics in a particular course, analyze the leadership and team-based qualities of a group of students, and analyze patterns and trends in female student participation. The experimental analysis revealed that participation in online discussion forums has a positive impact on the students' grades; the study of interaction patterns exhibit similar insights. In conclusion, this research study validates that the analysis of structured discussions can provide useful insights into changes in student collaboration patterns over time and students' sense of belongingness for pedagogical benefits.