No abstract

No abstract

Technical educations often exhibit poor student performance and consequently high rates of attrition. Providing students with early feedback on their learning progress can assist them in self-study activities or in their decision-making process regarding a change in educational direction. In this paper, we present a set of instruments designed to identify at-risk undergraduate students in a Problem-based Learning (PBL) university, using an introductory programming course as a case study. Collectively, these instruments form the basis of a proposed learning ecosystem designed to identify struggling students by predicting their final exam grades in this course. We implemented this ecosystem and analyzed how well the obtained data predicted the final exam scores. Best-subset-regression and lasso regressions yielded several significant predictors. Apart from relevant predictors known from the literature on exam scores and drop-out factors such as midterm exam results and student retention factors, data from self-assessment quizzes, peer reviewing activities, and interactive online exercises helped predict exam performance and identified struggling students.

Technical educations often experience poor student performance and consequently high rates of attrition. Providing students with early feedback on their learning progress can assist students in self-study activities or in their decision-making process regarding a change in educational direction. In this paper, we present a set of instruments designed to identify at-risk undergraduate students in a Problem-based Learning (PBL) university, using an introductory programming course between two campus locations as a case study. Collectively, these instruments form the basis of a proposed learning ecosystem designed to identify struggling students by predicting their final exam grades in this course. We implemented this ecosystem at one of the two campus locations and analyzed how well the obtained data predicted the final exam grades compared to the other campus, where midterm exam grades alone were used in the prediction model. Results of a multiple linear regression model found several significant assessment predictors related to how often students attempted self-guided course assignments and their self-reported programming experience, among others.

Deficits with time management and other cognitive functions can stem from multiple causes and be found across different diagnostic conditions. At the same time, cognitive function can differ within diagnostic classes, which calls for adaptable and personalized assistance. A great deal of literature on cognitive assistive technology (CAT) focus on diagnostic populations rather than cognitive impairments across different conditions. This study reports the initial steps towards a data-driven approach to map out the characteristics and behavior of users of a time management app, Tiimo, originally targeting children with ADHD. Based on results from a questionnaire and analysis of user activity data, findings indicate a tendency of attracting a more heterogeneous user population compared to the originally intended target group, thus supporting the need for a more complex and data-driven 'design for all' approach to CAT rather than delimitations based on diagnostic groups. Preliminary findings from the analysis of activity data across user groups and diagnoses show that users generally schedule fewer than five daily activities and most often in the morning, suggesting a potential emphasis on support particularly during morning routines. However, the analysis also highlights the need for more data points to enable assessment of progress, motivation, and effectiveness of the technology. Next steps include a more detailed analysis of user activity that takes different types of behavior and other relevant factors into account by applying NLP to further develop data-driven approaches to user profiling and personalization in time management apps for neurodivergent users.