26 January 2024 in Journal of Learning Analytics
Predictive learning analytics has been widely explored in educational research to improve student retention and academic success in an introductory programming course in computer science (CS1). General-purpose and interpretable dropout predictions still pose a challenge. Our study aims to reproduce and extend the data analysis of a privacy-first student pass–fail prediction approach proposed by Van Petegem and colleagues (2022) in a different CS1 course. Using student submission and self-report data, we investigated the reproducibility of the original approach, the effect of adding self-reports to the model, and the interpretability of the model features. The results showed that the original approach for student dropout prediction could be successfully reproduced in a different course context and that adding self-report data to the prediction model improved accuracy for the first four weeks. We also identified relevant features associated with dropout in the CS1 course, such as timely submission of tasks and iterative problem solving. When analyzing student behaviour, submission data and self-report data were found to complement each other. The results highlight the importance of transparency and generalizability in learning analytics and the need for future research to identify other factors beyond self-reported aptitude measures and student behaviour that can enhance dropout prediction.
12 December 2025 in Technological Forecasting and Social Change
6 October 2025 in International Journal of Mathematical Education in Science and Technology
19 July 2025 in European Journal of Engineering Education
22 October 2026 in Journal of Engineering Education
Background: Active learning and student engagement are recognized as essential in engineering education and mathematics learning. Research is needed to reveal how different practices and events in university mathematics classrooms promote students' cognitive engagement to identify good practices for enhancing engagement. Purpose: This study aimed to identify transitions in student cognitive engagement and how different classroom events precede transitions into higher cognitive engagement modes in large and small group learning settings in university mathematics classrooms. Design: Students' cognitive engagement was coded according to the interactive‐constructive‐active‐passive (ICAP) theory to understand students' overall engagement in real time, and transitions from lower to higher cognitive engagement modes were qualitatively analyzed. The video data were collected in an introductory mathematics course part of an engineering program. Participants were first‐year software engineering students. Results: In the large group setting, transitions into active and constructive modes were the most represented. In particular, the teacher's prompts preceded students' transitions into higher engagement modes. In the small group setting, transitions into active and interactive modes were the most represented, and the role of classmates' prompts was highlighted in transitions into higher modes. Interactive engagement was prompted mostly by classmates' prompts or students' own initiatives. Conclusions: Different learning settings have special characteristics when it comes to enhancing students' cognitive engagement. Findings indicate that teachers' constructive prompts and classroom organization contribute significantly to transitions in student engagement in the large group setting. In the small group setting, classmates' prompts were emphasized in promoting transitions, especially into the interactive level.
29 April 2026 in Professional Development in Education
Incorporating teaching practices that develop students’ information and communication technology (ICT)-related skills offers various benefits, from increased academic achievement to enhanced motiva...