Personalized and Automated Feedback in Summative Assessment Using Recommender Systems

In this study we explore the use of recommender systems as a means providing automated and personalized feedback to students following summative assessment. The intended is set test questions ( items ) for each student that they could benefit from practicing with. Recommended can be beneficial support their learning process by targeting specific gaps in knowledge, especially when there little time get instructors. are recommended using several commonly used system algorithms, based on students' scores results show context Dutch secondary education final examinations, item recommendations made with an acceptable level model performance. Furthermore, it does not take computationally complex do so: simple baseline which takes into account global, student-specific, item-specific averages obtained similar performance more models. Overall, conclude promising tool helping combining multiple data sources new methodologies, without putting additional strain