Creating and Collecting e-Learning Event Logs to Analyze Learning Behavior of Students through Process Mining

Abstract

Many traditional educational management models are being switched or shifted into online platforms; thus, assessing behavioral aspects of learners is essential to improving the quality of online teaching and learning processes. Currently, a problem in managing online teaching of courses is that instructors do not have the appropriate tools and techniques to be fully aware of students’ behavioral patterns in a data-driven and process-aware approach. This study is divided into three main parts. In the first part, a dataset of online students is transformed and preprocessed. In the second part, the Fuzzy Miner algorithm supported by Fluxicon Disco is applied to the dataset to understand the learning process of the students in terms of the duration and length of the tutorial videos watched online (i.e., fully watched, partially watched, paused, and resumed intervals) and in terms of the frequencies of all activities. In the third part, a comparison between behavioral patterns of high-performance group of students versus their low-performance counterparts attending the same course was conducted, and we used the Dotted Chart Analysis technique supported by ProM to conduct and make the comparisons. The results of the study showed significant differences between the two groups in terms of the duration spent on the tutorial videos and in terms of the sequence and order of the activities performed and executed. The findings of the research can be used by instructors, administrators, and educational managers to improve the course curriculum management process or to boost effective coaching and teaching styles, leading to the optimization of students’ learning process by increasing educators’ awareness about students’ weaknesses and strengths.

Analysis of Student Learning Behavior Portrait Based on Big Data Technology

“…Big data technology equips educators and researchers with the tools to identify intricate patterns in student behavior that were previously inaccessible. It facilitates the measurement of engagement levels, tracking of progress, and identification of at-risk students, thereby enhancing the potential for personalized learning experiences [7].…”

“…Notable research in this field has demonstrated the potential of big data analytics to predict student success and failure, enabling early interventions to improve educational outcomes. Additionally, it has shed light on the influence of external factors, such as socioeconomic status and access to technology, on learning behavior [6,7,8,9].…”

The Effect of E-learning and Students’ Digital Literacy towards Their Learning Outcomes

“…It reflects that digital literacy is a key role in using e-learning for optimizing hybrid learning since it is viewed as the ability in utilizing technological means or digital devices effectively and efficiently to find and deliver information (Tang & Chaw, 2016). Therefore, students' digital literacy is the main question that needs to be concerned by the teacher related to the assistance or effectiveness of e-learning as a media for conducting hybrid learning (Nammakhunt et al, 2023;Yang et al, 2014).…”