Public defence in Computer Science, M.Sc. Sami Sarsa

Title of the doctoral thesis: Machine Learning Applications Supporting Large Scale Programming Education

Doctoral student: Sami Sarsa
Opponent: Prof. Tiffany Barnes, North Carolina State University, USA
Custos: Prof. Lauri Malmi, Aalto University School of Science, Department of Computer Science

One major challenge in modern education is the provision of effective individualized education at scale. Various machine learning methods have made it possible to develop effective adaptive and intelligent learning systems. In recent years, the emergence of deep learning models, and more recently large language models, have brought new opportunities — and also challenges — for educators and learning system developers. 

This dissertation explores the use of machine learning to improve large scale programming education across various subject areas. The conducted research provides new insights and evaluations on how machine learning models can be applied for personalized learning, early warning systems, and improving the timeliness of automated feedback. 

The dissertation also introduces a novel large language model-based method for automatically generating programming exercises and code explanations. The results of the included studies show that large language models can be employed to generate diverse and coherent explanations and personalised exercises, albeit not entirely without human supervision. 

The findings of the dissertation are relevant particularly in integrating AI to tailor learning and tutoring for large audiences, for example in intelligent tutoring systems. The findings can help in facilitating better learner engagement and educational outcomes, as well as reducing the workload of educators in providing up-to-date meaningful educational content.

Key words: computer science education, learning analytics, machine learning, large language models, learner modeling, automated feedback, robosourcing

Thesis available for public display 10 days prior to the defence at: https://aaltodoc.aalto.fi/doc_public/eonly/riiputus/

Contact information: 

Doctoral theses in the School of Science: https://aaltodoc.aalto.fi/handle/123456789/52