Utilising behavioural analytics in a blended programming learning environment

In this work, we study students' behaviours from a blended programming learning environment that integrates learning analytics across physical and digital learning spaces. We designed a classroom study and collected data from a computer science class. Students' reviewing and reflecting behaviours, based on the use of a home-grown educational technology were tracked and modelled. Moreover, students' reviewing efforts, in terms of frequency, timing, and the associations with their academic performances were analysed. Results showed that high- and low-level students had distinct reviewing strategies. High-level students were more vigilant in reviewing. When they reviewed persistently, they achieved higher academic performances. Overall, students put extra emphasis on reviewing prior to the exams and the efforts demonstrated the desire to review formal assessments regardless of if they were graded for academic performance. In addition, all students paid more attention to reviewing quizzes and exams toward the end of the semester.