International Laboratory of Research and Design in elearning

Publications

• Article

  Boitcov M., Kapuza A., Al-Safi H. et al.

  Left unread: how message orientation shapes engagement in adaptive nudging systems

  Sustaining behavioural engagement remains a persistent challenge in online learning, where participation often declines over time despite widespread use of message-based nudges as a scalable form of support. Existing research has typically examined message content and learner interactivity in isolation, making it difficult to understand how these features jointly relate to behavioural engagement in adaptive systems that tailor messages to learners' prior behaviour. This study examines how reply behaviour is associated with subsequent behavioural engagement in a behaviour-triggered messaging system that differentiates between reinforcing and concern-oriented messages. During a four-week intervention in an online preparatory course, 144 students received supportive messages triggered by recent learning management system activity. All messages invited replies, enabling both one-way and two-way communication. Engagement was measured using the Coefficient of Retention (COR), a longitudinal composite indicator, capturing persistence across homework completion, webinar participation, and platform use. Multilevel regression analyses showed that replying to a message was not uniformly associated with higher engagement once prior engagement and homework performance were accounted for. However, this association differed by message type. Replies to reinforcing messages were marginally associated with higher subsequent engagement, whereas replies to concern-oriented messages were associated with lower engagement relative to non-replies. By contrast, non-response to concern-oriented messages was linked to modest increases in engagement. Overall, the findings suggest that the relationship between interactivity and engagement depends on message orientation within adaptive nudging systems.

  Interactive Learning Environments. 2026. P. 1-14.

• Article

  Gorbunova A., Adamovich K., Savelyev A. et al.

  Behavior patterns characterize students’ choices and relate to cognitive load and performance in learner-controlled environments

  Asynchronous online learning environments offer flexibility for students to navigate learning at their own pace, resulting in diverse behavioral patterns that can significantly impact cognitive load and academic performance. However, limited research has explored how learner-controlled environments shape these patterns and their relationship to learning outcomes and levels of cognitive load. This study investigates behavioral patterns in an online asynchronous graduate law class (n = 90) at a large university, analyzing data from a learning management system to categorize students into clusters based on their interactions with instructional components (e.g., video lectures, video-based examples, and problem-solving tasks). Cluster analysis revealed three distinct patterns: balanced learners, who achieved the highest performance; practice-oriented learners, who exhibited lower intrinsic cognitive load; and classic learners, characterized by comparatively lower extraneous cognitive load. However, these differences in extraneous load were not statistically significant between clusters, suggesting that the additional cognitive demands of learner control may have imposed similar baseline levels of extraneous load regardless of behavior pattern. Contrary to expectations, learner behavior patterns extended beyond example-based and problem-solving-first approaches, highlighting greater variability in learner strategies. These findings underscore the importance of understanding instructional paths in learner-controlled environments and how behavioral patterns can interact with both cognitive load and learning outcomes.

  Internet and Higher Education. 2026. Vol. 69.

• Article

  K. Adamovich, A. Getman, A. Kapuza et al.

  Does slow and steady win the race? The relationship between adult EFL learners’ time-related task strategies and achievement

  Despite the known importance of out-of-class assignments in academic success, research on how adult students engage with tasks in online learning is limited. Students use various time-related engagement strategies, from completing assignments in advance to delaying them until the last minute. Research is unclear about what strategies are more beneficial in terms of academic achievement. In this study, we examine task engagement strategies of 70,527 learners and their relationship with academic achievement. We use LMS data from an online English language learning platform. We identified three distinct task engagement strategies, including ‘Last minute Larry’, ‘Slow and steady’, and ‘Early bird’ students. While ‘Early birds’ complete the most tasks, their academic achievement is comparable to ‘Last minute Larrys’. ‘Slow and steady’ students are the most academically successful. Our study contributes to the discussion on time-related task strategies, shedding light on the latent efficacy of the slow pace of task completion.

  Language Learning Journal. 2025. P. 1-12.

• Article

  Shulgina G., Adamovich K., Zhang H. et al.

  Comment Type Matters: Analysing the Implementation of Summary, Problem/Solution, and Praise Comments in Peer Feedback

  Prior research has suggested that the receipt of peer comments and their subsequent implementation may help to improve student’s writing performance. However, comments may vary in terms of content and subsequent effects of their implementation on writing quality. Currently, there is a lack of research investigating how comments providing praise, summary, and information about problems and solutions are related to the subsequent text revision and writing improvement. Therefore, this study examines the online peer feedback session of 187 students taking academic writing classes at a Korean university. It aims to investigate the relationship between the receipt of comments providing praise, summary, and information about problems and solutions, as well as their implementation and student writing performance. The results showed that there is no relationship between the number of received comments and student writing performance. However, the more comments students implemented, the lower their writing performance was. With regards to the type of comments, summary comments, and comments detecting problems and/or solutions were more likely to be implemented when compared with praise comments. The receipt of comments about problems and/or solutions had a significantly negative relationship with student writing performance, whereas their implementation was positively related to this variable.

  Active Learning in Higher Education. 2025.

• Article

  Kapuza A., Getman A., Kotlikova A. et al.

  Predicting students engagement in asynchronous online learning: a mixed-method approach

  Predicting the level of student learning engagement in online learning is crucial for student success, especially for asynchronous courses. While digital traces can track students’ activity on the platform and help to measure the engagement level, they could provide contradictory results, so it is crucial to incorporate complementary methods which can triangulate the findings obtained from digital traces. This study aimed to develop and validate a model to determine the level of learning engagement in adult learners on an asynchronous online platform using a mixed-method approach. Data from digital traces, surveys, and interviews were combined. The study involved 2234 students and employed Extreme Gradient Boosting and Logistic Regression with L2 regularisation models to predict the level of engagement. The Extreme Gradient Boosting model more accurately predicted students in the low engagement group, providing crucial support for potentially vulnerable students. The number of finished homework assignments and attempts were found to increase the probability of high engagement. The diversity of activities, such as access to text materials, played a pivotal role in sustaining engagement. Interviews corroborated these results, suggesting the model effectively reflects engagement levels. The article discusses implications for constructing similar models in future research.

  Educational Technology Research and Development. 2025.