Using Educational Data Mining Techniques to Identify Profiles in Self-Regulated Learning: An Empirical Evaluation

Abstract

With the increased emphasis on the benefits of self-regulated learning (SRL), it is important to make use of the huge amounts of educational data generated from online learning environments to identify the appropriate educational data mining (EDM) techniques that can help explore and understand online learners’ behavioral patterns. Understanding learner behaviors helps us gain more insights into the right types of interventions that can be offered to online learners who currently receive limited support from instructors as compared to their counterparts in traditional face-to-face classrooms. In view of this, our study first identified an optimal EDM algorithm by empirically evaluating the potential of three clustering algorithms (expectation-maximization, agglomerative hierarchical, and k-means) to identify SRL profiles using trace data collected from the Open University of the UK. Results revealed that agglomerative hierarchical was the optimal algorithm, with four clusters. From the four clusters, four SRL profiles were identified: poor self-regulators, intermediate self-regulators, good self-regulators, and exemplary self-regulators. Second, through correlation analysis, our study established that there is a significant relationship between the SRL profiles and students’ final results. Based on our findings, we recommend agglomerative hierarchical as the optimal algorithm to identify SRL profiles in online learning environments. Furthermore, these profiles could provide insights on how to design a learning management system which could promote SRL, based on learner behaviors.

Practice and Exploration of Teaching Mental Health Education for College Students Based on Data Mining Algorithm

“…Most scholars believe that the characteristics of current crimes committed by university students are increasing in number, diverse types, highly intelligent and brutal crime methods, and the expansion of the subjects involved in crimes [13] argues that "college students' crimes present characteristics such as the young age of the offender, impulsiveness, extreme ego and individualism, concentration of crimes in property and violence type, clear purpose of committing crimes, and simple motives for committing crimes." [14] summarises the characteristics of crime among university students as: diversity, passion, high intelligence, and cruelty. [15] argues that, "College students are socially inclined to commit crimes.…”

The Importance of a Learner Management System in Implementing Data-driven Instruction in Higher Education Institutions

“…It has different features including chats, emails, wikis, forums, assignments, quizzes and blogs. These features allow learners to be able to be active while achieving effective learning and engagement (Araka et al, 2021). Furthermore, the LMS features assist in improving self-regulated learning.…”

Predicting time‐management skills from learning analytics

“…Among other things, trace data measuring the average session length, and the number of weeks the student spent at least 48 minutes studying were successfully used to build an early warning system for students prone to failing the course. Learning analytics has also been used to cluster students based on the extent to which they displayed self‐regulating behaviour (Araka et al, 2022; Kim et al, 2018). Kim et al (2018) used indicators of help‐seeking, time‐investment, and study regularity to successfully group students into self‐regulated, partially self‐regulated, and non‐self‐regulated students.…”