Effects of Response-Driven Feedback in Computer Science Learning

This paper presents the results of a project on generating diagnostic feedback for guided learning in a first-year course on programming and a Master's course on software quality. An online multiple-choice questions (MCQs) system is integrated with neural network-based data analysis. Findings about how students use the system suggest that the feedback is effective in addressing the level of knowledge of the individual and guiding him/her toward a greater understanding of particular concepts. In contrast, there is no evidence that learning required in programming problems, where students develop higher-level thinking according to Bloom's taxonomy, was exercised by using MCQs.