AI-assisted programming question generation: Constructing semantic networks of programming knowledge by local knowledge graph and abstract syntax tree

• Published in: Journal of research on technology in education Vol. 55; no. 1; pp. 94 - 110
• Main Authors: Chung, Cheng-Yu, Hsiao, I-Han, Lin, Yi-Ling
• Format: Journal Article
• Language: English
• Published: Eugene Routledge 03.01.2023; Taylor & Francis Ltd
• Subjects: Artificial Intelligence; Barriers; Computational Linguistics; Computer programming; Computer Science Education; computing education; Educational Resources; Educational technology; Feedback (Response); Graphs; Heterogeneous Grouping; Influence of Technology; Introductory Courses; knowledge graph; Programming; Question generation; Questioning Techniques; Semantic web; Syntax; Teacher Attitudes; Teaching methods
• ISSN: 1539-1523; 1945-0818
• DOI: 10.1080/15391523.2022.2123872

Creating practice questions for programming learning is not an easy job. It requires the instructor to diligently organize heterogeneous learning resources. Although educational technologies have been adopted across levels of programming learning, programming question generation (PQG) is still predominantly performed by instructors without advanced technological support. This study proposes a knowledge-based PQG model that aims to help the instructor generate new programming questions and expand the assessment items by the Local Knowledge Graph and Abstract Syntax Tree. A group of experienced instructors was recruited to evaluate the PQG model and expressed significantly positive feedback on the generated questions.