An educational data mining plugin for Moodle: enhancing self-regulated learning through automated interventions
Eric ArakaPurpose
The purpose of this study was to develop and evaluate an educational data mining (EDM) plugin for the Moodle learning management system (LMS) aimed at enhancing students' self-regulated learning (SRL) strategies. The study sought to address the underutilization of LMS features by providing automated, individualized learner interventions and instructor support. By integrating SRL-focused analytics and feedback, the plugin helps learners monitor and control their cognition, behavior and motivation in online learning environments.
Design/methodology/approach
The study employed the Integrated Design Process to design and develop an EDM plugin for the Moodle LMS. A true experimental research design was used to evaluate the plugin's effectiveness in enhancing SRL strategies. The experiment involved university students enrolled in a 12-week data science with Python course. Data were collected through time series logs, post-study surveys and semi-structured interviews. Quantitative and qualitative analyses were conducted to assess the plugin's impact on students' SRL behaviors, satisfaction and engagement with LMS features.
Findings
The results indicate that the EDM plugin effectively enhanced students' SRL strategies within the Moodle LMS. Time series analysis showed increased engagement with key LMS features, while qualitative data revealed improved learner motivation, planning and monitoring behaviors. Content analysis from the post-study survey and interviews confirmed that students were satisfied with the individualized SRL interventions and appreciated the regular reminders and feedback provided by the plugin. Overall, the tool fostered greater autonomy and proactive learning behaviors in the online learning environment.
Research limitations/implications
The study was limited to a single course with a small sample of university students, which may affect the generalizability of the findings to other disciplines or learning contexts. Additionally, the study's duration was restricted to 12 weeks, limiting the long-term assessment of SRL development. Despite these limitations, the findings demonstrate the potential of EDM tools to enhance SRL in online environments. Future research should test the plugin across diverse courses and institutions and explore adaptive algorithms for more personalized SRL interventions.
Practical implications
The study provides practical insights for educators and instructional designers seeking to enhance SRL in online environments. The developed plugin demonstrates how EDM can automate personalized learner support by offering timely feedback, reminders and interventions that encourage active engagement with LMS features. Instructors can use similar tools to monitor learner progress and provide data-driven guidance, reducing the need for manual oversight. Institutions adopting such systems can improve learner autonomy, motivation and overall course performance while promoting a more adaptive and supportive online learning experience.
Social implications
The study highlights the potential of technology-enhanced learning tools to promote equitable access to quality education through improved learner autonomy and engagement. By fostering SRL skills, the plugin empowers students to take ownership of their learning 2014 an essential competency for lifelong learning in the digital era. Such innovations can reduce educational disparities by supporting diverse learners with individualized interventions regardless of time or location. Broad adoption of similar tools can contribute to developing more resilient self-directed learners, ultimately strengthening digital literacy and employability in a rapidly evolving knowledge-based society.
Originality/value
This study contributes to the growing field of technology-enhanced learning by integrating EDM with SRL support in the Moodle LMS through a custom-built plugin. Unlike previous studies that focused on static analytics or instructor-driven interventions, this research introduces an automated, data-informed approach that provides individualized learner feedback and reminders in real time. The plugin's design and empirical validation demonstrate a novel method for promoting SRL behaviors in online courses, offering both theoretical insights and practical tools for improving learner autonomy and engagement in digital learning environments.