Recent research has shown the great potential of automatic feedback in education. This paper presents SOBO, a bot we designed to automatically provide feedback on code quality to undergraduate students. SOBO has been deployed in a course at the KTH Royal Institute of Technology in Sweden with 130+ students. Overall, SOBO has analyzed 1687 GitHub repositories and produced 8443 tailored code quality feedback messages to students. The quantitative and qualitative results indicate that SOBO effectively nudges students into adopting code quality best practices, without interfering with pedagogical objectives or adding a teaching burden. From this experience, we provide guidelines on how to design and deploy teaching bots in programming courses.

Our original paper can be found via https://ieeexplore.ieee.org/document/10195904.

To summarize, we make the following contributions: - We introduce SOBO, a new automatic feedback tool. SOBO is publicly available at https://github.com/eclipse/repairnator/tree/master/doc/sobo. - We propose guidelines for further development of bots for computer science education, targeting the problem with tool adoption. - We report the original results of the evaluation of SOBO’s effectiveness in nudging the adoption of code quality practices. The results of this study and our survey show that students find SOBO helpful.