Technology Category
Cognitive Modeling & Cognitive Systems: Simulating Human BehaviorMachine Learning: Life-Long and Continual LearningApplication Domains: Humanities & Computational Social Science
Understanding Self-Regulated Learning Behavior Among High and Low Dropout Risk Students During CS1: Combining Trace Logs, Dropout Prediction and Self-Reports
🤖 AI Summary
High attrition rates in introductory computer science (CS1) courses stem from students’ insufficient self-regulated learning (SRL) competencies, yet existing research lacks fine-grained characterization of when difficulties emerge, how they manifest behaviorally, and when interventions remain feasible. Method: This study integrates fine-grained behavioral logs from virtual learning environments, a dynamic dropout-risk stratification model, and SRL self-report questionnaires—thereby unifying SRL theory, real-time behavioral tracking, and risk-evolution analysis for the first time. Using learning analytics, behavioral sequence mining, and a mixed-methods approach (quantitative trajectory clustering plus qualitative strategy interpretation), we identify three distinct SRL strategy profiles among low-risk students and nine among high-risk students. Contribution/Results: We uncover two critical behavioral signatures: “recoverable transient failure” and “critical attrition behaviors.” These findings enable instructors to detect at-risk students earlier and intervene more promptly and precisely, substantially enhancing the timeliness and targeting of instructional support.
Technology Category
Application Category
📝 Abstract
The introductory programming course (CS1) at the university level is often perceived as particularly challenging, contributing to high dropout rates among Computer Science students. Identifying when and how students encounter difficulties in this course is critical for providing targeted support. This study explores the behavioral patterns of CS1 students at varying dropout risks using self-regulated learning (SRL) as the theoretical framework. Using learning analytics, we analyzed trace logs and task performance data from a virtual learning environment to map resource usage patterns and used student dropout prediction to distinguish between low and high dropout risk behaviors. Data from 47 consenting students were used to carry out the analysis. Additionally, self-report questionnaires from 29 participants enriched the interpretation of observed patterns. The findings reveal distinct weekly learning strategy types and categorize course behavior. Among low dropout risk students, three learning strategies were identified that different in how students prioritized completing tasks and reading course materials. High dropout risk students exhibited nine different strategies, some representing temporary unsuccessful strategies that can be recovered from, while others indicating behaviors of students on the verge of dropping out. This study highlights the value of combining student behavior profiling with predictive learning analytics to explain dropout predictions and devise targeted interventions. Practical findings of the study can in turn be used to help teachers, teaching assistants and other practitioners to better recognize and address students at the verge of dropping out.
Problem
Research questions and friction points this paper is trying to address.
Analyzing self-regulated learning in CS1 students to predict dropout risks
Identifying distinct learning strategies among high and low dropout risk students
Combining behavior profiling and predictive analytics for targeted interventions
Innovation
Methods, ideas, or system contributions that make the work stand out.
Analyzed trace logs and task performance data
Combined learning analytics with self-reports
Profiled student behavior for dropout prediction
🔎 Similar Papers
No similar papers found.
