Evaluating Student Response Driven Feedback in a Programming Course

Abstract

This paper presents an experience of generating diagnostic feedback for guided learning in an introductory programming course. An on-line Multiple Choice Questions (MCQs) system is integrated with a neural network based data analysis. Some empirical results about how students use the system in a CS1 course are presented. Research with an experimental group of 61 students suggests that the feedback addresses the level of knowledge of the individual and guides them towards a greater understanding of particular concepts. Moreover the approach proposed promotes the students' interest and produces statistically significant differences in the scores between the experimental group and control group.