Monitoring Class Activity and Predicting Student Performance Using Moodle Action Log Data

  • Rodolfo C. Raga Jr Department of Computer Studies and Engineering, Jose Rizal University
  • Jennifer D. Raga Management and Information Systems Department Western Group of Companies

Abstract

Purpose – This paper proposes a novel approach for processing course log data obtained from Moodle-based blended courses in order to visualize patterns of student activity within the online environment and to determine whether these log data can be used to predict student academic performance.

Method – Logs of student activities were summarized and processed using the Vector Space Model approach. This resulted in a novel vector-based form of representation which can be used to map students’ activity in a latent activity space given a set of activity dimensions. An enriched form of this representation was also generated by processing the DateTime and IP address metadata for the purpose of developing classification/predictive model of students’ performance. 

Results – The activity space coupled with a one-hot vector representation for each unique activity dimension can be used to visualize the differences in level and type of activity preferences of students. Experiments using several machine learning algorithms indicate that the generated model can modestly distinguish between sets of activities that lead to High, Low, or Failed performances.

Conclusion – The development of easily interpretable graphics that can depict trends in student activity is a useful tool for instructors handling blended courses. It can provide constant monitoring of course progression with minimal effort and enable instructors to determine whether and how the environment actually affects student performance.

Recommendations – Further work on refining the process applied to the data is recommended. The log data should be time-sliced and processed to determine whether and how the student’s level and type of activity changes over time. More powerful machine learning classification techniques shouldalso be tested to determine whether it can improve the classification accuracy.

Research Implications – These types of visualizations and predictive models could be used to monitor the student or class which requires immediate and specific pedagogical adjustments.

Author Biographies

Rodolfo C. Raga Jr, Department of Computer Studies and Engineering, Jose Rizal University

Rodolfo C. Raga Jr. received his PhD in Computer Science degree from the De La Salle University, Manila, Philippines in 2013. He’s an Associate Professor in the College of Computer Studies and Engineering of Jose Rizal University, Philippines. His research interests lie in natural language processing, educational data mining, learning analytics, and academic e-learning.

Jennifer D. Raga, Management and Information Systems Department Western Group of Companies

Jennifer D. Raga received her Master in Information Technology degree from the University of LaSalette, Santiago City, Philippines in 2009. She is currently the MIS Manager at Western Marketing Corporation and a part-time IT lecturer. Her research interests lie in knowledge management, business analytics, and corporate e-learning.

Published
2017-12-22
How to Cite
RAGA JR, Rodolfo C.; RAGA, Jennifer D.. Monitoring Class Activity and Predicting Student Performance Using Moodle Action Log Data. International Journal of Computing Sciences Research, [S.l.], v. 1, n. 3, p. 1-16, dec. 2017. ISSN 2546-115X. Available at: <https://stepacademic.net/ijcsr/article/view/33>. Date accessed: 23 jan. 2018.
Section
Articles