Enhancing Learning Outcomes within a Large-Scale Online Learning System through AI-Powered Feedback

Aylin Ozturk, Robin Schmucker, Tom Mitchell
Proceedings of the Innovation and Responsibility in AI-Supported Education Workshop, PMLR 273:255-259, 2025.

Abstract

Building on prior research, which demonstrated the effectiveness of a learning analytics-based feedback system in improving learner engagement and learning outcomes, this study addresses scalability challenges by automating feedback authoring using generative AI. Focusing on critical issues in distance education, including limited academic support, social isolation, and reduced learner motivation, we design and evaluate an AI-powered feedback system within a large-scale online learning environment. This study utilizes input data comprising learners’ online learning environment interactions, learning material engagement patterns, academic performance metrics, behavioral indicators, and demographic characteristics. The system generates AI-powered personalized feedback interventions based on the ARCS-V Motivation Model, Self-Regulated Learning principles, and Nudge Theory as its primary outputs. To assess the system’s effectiveness, more than 30,000 learners at a large distance education university will be randomly assigned to experimental and control groups. Preliminary work demonstrated the system’s readiness for a pilot evaluation. The next steps include assessing the system’s impact on diverse learner subgroups and refining system design based on user feedback. The study aims to advance our understanding of how AI-powered, personalized feedback influences self-regulated learning, motivation, and learning outcomes in online environments.

Cite this Paper

BibTeX
@InProceedings{pmlr-v273-ozturk25a, title = {Enhancing Learning Outcomes within a Large-Scale Online Learning System through AI-Powered Feedback}, author = {Ozturk, Aylin and Schmucker, Robin and Mitchell, Tom}, booktitle = {Proceedings of the Innovation and Responsibility in AI-Supported Education Workshop}, pages = {255--259}, year = {2025}, editor = {Wang, Zichao and Woodhead, Simon and Ananda, Muktha and Mallick, Debshila Basu and Sharpnack, James and Burstein, Jill}, volume = {273}, series = {Proceedings of Machine Learning Research}, month = {03 Mar}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v273/main/assets/ozturk25a/ozturk25a.pdf}, url = {https://proceedings.mlr.press/v273/ozturk25a.html}, abstract = {Building on prior research, which demonstrated the effectiveness of a learning analytics-based feedback system in improving learner engagement and learning outcomes, this study addresses scalability challenges by automating feedback authoring using generative AI. Focusing on critical issues in distance education, including limited academic support, social isolation, and reduced learner motivation, we design and evaluate an AI-powered feedback system within a large-scale online learning environment. This study utilizes input data comprising learners’ online learning environment interactions, learning material engagement patterns, academic performance metrics, behavioral indicators, and demographic characteristics. The system generates AI-powered personalized feedback interventions based on the ARCS-V Motivation Model, Self-Regulated Learning principles, and Nudge Theory as its primary outputs. To assess the system’s effectiveness, more than 30,000 learners at a large distance education university will be randomly assigned to experimental and control groups. Preliminary work demonstrated the system’s readiness for a pilot evaluation. The next steps include assessing the system’s impact on diverse learner subgroups and refining system design based on user feedback. The study aims to advance our understanding of how AI-powered, personalized feedback influences self-regulated learning, motivation, and learning outcomes in online environments.} }
Endnote
%0 Conference Paper %T Enhancing Learning Outcomes within a Large-Scale Online Learning System through AI-Powered Feedback %A Aylin Ozturk %A Robin Schmucker %A Tom Mitchell %B Proceedings of the Innovation and Responsibility in AI-Supported Education Workshop %C Proceedings of Machine Learning Research %D 2025 %E Zichao Wang %E Simon Woodhead %E Muktha Ananda %E Debshila Basu Mallick %E James Sharpnack %E Jill Burstein %F pmlr-v273-ozturk25a %I PMLR %P 255--259 %U https://proceedings.mlr.press/v273/ozturk25a.html %V 273 %X Building on prior research, which demonstrated the effectiveness of a learning analytics-based feedback system in improving learner engagement and learning outcomes, this study addresses scalability challenges by automating feedback authoring using generative AI. Focusing on critical issues in distance education, including limited academic support, social isolation, and reduced learner motivation, we design and evaluate an AI-powered feedback system within a large-scale online learning environment. This study utilizes input data comprising learners’ online learning environment interactions, learning material engagement patterns, academic performance metrics, behavioral indicators, and demographic characteristics. The system generates AI-powered personalized feedback interventions based on the ARCS-V Motivation Model, Self-Regulated Learning principles, and Nudge Theory as its primary outputs. To assess the system’s effectiveness, more than 30,000 learners at a large distance education university will be randomly assigned to experimental and control groups. Preliminary work demonstrated the system’s readiness for a pilot evaluation. The next steps include assessing the system’s impact on diverse learner subgroups and refining system design based on user feedback. The study aims to advance our understanding of how AI-powered, personalized feedback influences self-regulated learning, motivation, and learning outcomes in online environments.
APA
Ozturk, A., Schmucker, R. & Mitchell, T.. (2025). Enhancing Learning Outcomes within a Large-Scale Online Learning System through AI-Powered Feedback. Proceedings of the Innovation and Responsibility in AI-Supported Education Workshop, in Proceedings of Machine Learning Research 273:255-259 Available from https://proceedings.mlr.press/v273/ozturk25a.html.

Related Material