Collaborative Research: Learning Software Engineering by Contributing to Real Projects With Chatbot Assistance

Open Source Software (OSS) is an economic driving force providing software systems used through the entire development stack, from operating system kernels to sophisticated end-user applications. It is also an important platform for education. A large number of young developers join open source projects to improve their programming and other software engineering skills. It is not surprising, therefore, that many software engineering educators want to use OSS projects as a training ground for students to gain experience with real world software development problems. These experiences carry the added benefit that students contribute to the evolution of projects relevant to society and their own interests. Successful participation in open source projects also increases students' chances for professional success. However, students onboarding to OSS face many difficulties. Project documentation is often lacking, and core developers have little time to effectively mentor students, since they often are volunteers contributing during their spare time. To better support students in their journey toward contributing to open source software, this project proposes to design, develop, and evaluate a conversational agent (chatbot). This project investigates how a conversational agent can be designed as an effective teaching aid for OSS contribution by understanding the needs and expectations of students and instructors, investigating how students verbalize their expectations and dialog with the agent, and how to design such an agent. To achieve these goals, the project employs a multi-method approach, including participatory design, prototyping, and technological evaluation. The project also investigates how effective a chatbot is in helping students learn how to contribute to an open source project in lab and classroom settings. This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.