Print Email Facebook Twitter Use of AI-driven code generation models in teaching and learning programming Title Use of AI-driven code generation models in teaching and learning programming: a systematic literature review Author Cambaz, Doga (TU Delft Electrical Engineering, Mathematics and Computer Science) Contributor Aivaloglou, E.A. (mentor) Zhang, X. (mentor) Viering, T.J. (graduation committee) Degree granting institution Delft University of Technology Programme Computer Science and Engineering Project CSE3000 Research Project Date 2023-06-28 Abstract The recent emergence of AI-driven code generation models can potentially transform programming education. To pinpoint the current state of research on using AI code generators to support learning and teaching programming, we conducted a systematic literature review with 21 papers published since 2018. The review presents the teaching and learning practices in programming education that utilize these models, the characteristics and performance indicators of the code generation models, and aspects to be considered when utilizing the models in programming education, including the risks and challenges of using code generation models for educational practices. AI code generators can be an assistive tool for both learners and instructors if the risks are mitigated. Subject programming educationcode generation modelsLarge Language ModelsArtificial Intelligence in education To reference this document use: http://resolver.tudelft.nl/uuid:4071531b-2dd0-4001-b67c-6351761d4821 Part of collection Student theses Document type bachelor thesis Rights © 2023 Doga Cambaz Files PDF DogaCambaz_Final_Paper.pdf 739.67 KB Close viewer /islandora/object/uuid:4071531b-2dd0-4001-b67c-6351761d4821/datastream/OBJ/view