Recommender Systems and Scratch: An Integrated Approach for Enhancing Computer Programming Learning

Abstract

Learning computer programming is a challenging process. Among the current approaches for overcoming this challenge, visual programming languages (VPLs), such as Scratch, have shown very promising results for beginners. Interestingly, some higher education institutions have started to use VPLs to introduce basic programming concepts, mainly in CS1 courses. However, an important issue regarding Scratchs usage in higher education environments is that students may feel unmotivated being confronted by programming exercises that do not fulfill their individual expectations. To try and overcome this barrier, we propose CARAMBA, a Scratch extension including an exercise recommender system. Based on features, such as taste and complexity , CARAMBA is able to personalize student learning with Scratch by suitably suggesting exercises for students. An in-depth evaluation was conducted about the effects of our proposal on both the learning of basic concepts of CS1 and the overall performance of students. We adopted an equivalent pretest-posttest design with 88 college students at an Ecuadorian university. Results confirm that recommending exercises in Scratch had a positive effect on students programming learning abilities in terms of pass rates. In totality, the pass rate achieved by our proposal was over 52%, which is 8% higher than the rate achieved during a previous experience using only Scratch (without recommendation) and 21% higher than the historical results of traditional teaching (without Scratch). Furthermore, we analyzed the degree of exploitation of CARAMBA by students to portray two facts: students actually used CARAMBA and there was a significant, positive correlation between the utilization of CARAMBA and the scores obtained by the students.