Learning logs collected by digital educational systems, increasingly deployed in educational settings, include clickstream logs recorded through page transitions in teaching materials and digital marker logs recorded by drawing a marker. A challenge with these learning logs is their low temporal and spatial resolutions. This paper proposes a…

Educational outcomes are heavily reliant on student engagement, yet this concept is complex and subject to diverse interpretations. The intricacy of the issue arises from the broad spectrum of interpretations, each contributing to the understanding of student engagement as both complex and multifaceted. Given the emergence and increasing use of…

Background: Many researchers work on the design and development of multimodal collaboration support systems with AI, yet very few of these systems are mature enough to provide actionable feedback to students in real-world settings. Therefore, a notable gap exists in the literature regarding students' perceptions of such systems and the feedback…

Understanding the relationship between student behaviors and learning outcomes is crucial for designing effective collaborative learning environments. However, collaborative learning analytics poses significant challenges, not only due to the complex interplay between collaborative problem-solving and collaborative dialogue but also due to the…

Actionability is a critical issue in learning analytics for driving impact in learning, bridging the gap between insights and improvement. This dissertation places actionability at the forefront, integrating it throughout the learning analytics process to fully leverage its potential. The study involves designing, developing, and implementing…

The effective use of self-regulation strategies has been considered significant in online learning environments. It is known that learners must be supported in this context. Academic help-seeking (AHS), as one of the main self-regulated learning strategies, is associated with academic success. However, learners may avoid seeking help for…

The temporal sequence of learning behavior is multidimensional and continuous in MOOCs. On the one hand, it supports personalized learning methods, achieves flexible time and space. On the other hand, it also makes MOOCs produce a large number of dropouts and incomplete learning behaviors. Dropout prediction and decision feedback have become an…

Due to the use of online learning platforms and learning management systems, students are now working unsupervised on quiz-taking platforms. These unsupervised online forms of assessment are replacing traditional supervised quizzes in conventional classrooms. It is unclear whether the quiz-taking behaviors of students in these settings align with…

The system architecture of big data in massive open online courses (BD-MOOCs System Architecture) is composed of six components. The first component was comprised of big data tools and technologies such as Hadoop, YARN, HDFS, Spark, Hive, Sqoop, and Flume. The second component was educational data science, which is composed of the following four…

Researchers in learning analytics have created indicators with learners' trace data as a proxy for studying learner behaviour in a college course. Student Approaches to Learning (SAL) is one of the theories used to explain these behaviours, distinguishing between deep, surface, and organized study. In Latin America, researchers have demonstrated…

Behavioural engagement as a predictor of academic success hinges on the interplay between effort and time. Exploring the longitudinal development of engagement is vital for understanding adaptations in learning behaviour and informing educational interventions. However, person-oriented longitudinal studies on student engagement are scarce.…

The application of student interaction data is a promising field for blended learning (BL), which combines conventional face-to-face and online learning activities. However, the application of online learning technologies in BL settings is particularly challenging for students with lower self-regulatory abilities. In this study, a personalized…

Combining nudge theory with learning analytics, 'nudge analytics', is a relatively recent phenomenon in the educational context. Used, for example, to address such issues as concerns with student (dis)engagement, nudging students to take certain action or to change a behaviour towards active learning, can make a difference. However, knowing who to…

Learners use digital media during learning for a variety of reasons. Sometimes media use can be considered "on-task," e.g., to perform research or to collaborate with peers. In other cases, media use is "off-task," meaning that learners use content unrelated to their current learning task. Given the well-known problems with…

The research presents precision education that aims to regulate students' behaviors through the learning analytics dashboard (LAD) in the AI-supported smart learning environment (SLE). The LAD basically tracks and visualizes traces of learning actions to make students aware of their learning behaviors and reflect these against the agreed goals.…