Adaptive remediation for novice programmers through personalized prescriptive quizzes

Learning to program is a cognitively demanding activity. Students need to combine mental models of various concepts and constructs to solve problems. Many students new to IT and CS programs have little or no prior experience with abstract reasoning and problemsolving. Instructors attempt to present the core concepts early to allow adequate time for students to complete their programming assignments. However, misconceptions of basic concepts formed in the early stages often get propagated blocking any further progress. Such students often begin to form poor opinions about their capability leading to low self-esteem and performance. This paper proposes a framework to help individual students to overcome their misconceptions through personalized prescriptive quizzes. These quizzes are generated by combining the rich meta-data captured by each quiz question with analysis of past responses to class quizzes. The personalized prescriptive quizzes generated helped to improve student engagement and performance substantially. Over 91% of the students surveyed indicated that personalized quizzes helped them to clarify their own misconceptions and made them more confident of their progress. Students using the prescriptive quizzes performed significantly better than others in subsequent class assessments and the final exam.