A lightweight and reliable framework toward real-time student engagement predictions in learning analytics

Long Hoang, George Shorten, Barry O’Sullivan, Hoang D. Nguyen
Reliable and Trustworthy Artificial Intelligence 2025, PMLR 310:24-33, 2025.

Abstract

Learning analytics can enable the provision of meaningful feedback based on the collected data, help educators to make decisions with and about learners, and improve learner performance. Student engagement predictions are a key factor in generating feedback for real-time learning analytics applications, such as dashboards. However, most previous work has been based on a heavy deep learning model, which results in challenges for deployment in real-time applications (a resource efficiency requirement in reliable AI). This paper proposes a lightweight deep-learning framework for predicting student engagement in video to address this limitation. The proposed method uses customized MobileNetV2 as the backbone, with an input size of 32 by 32 by 3, to extract features from consecutive video frames. Multi-Scale attention – Residual (MUSER) is used to capture global information and contextual representation of the extracted features. Finally, LSTM examines the temporal variations in video frames and yields the prediction result. We use the DAISEE dataset, the most popular dataset in the learning analytics community, to evaluate the proposed framework. Experimental results demonstrate that the proposed method achieves good accuracy while significantly reducing the model size compared to other approaches.

Cite this Paper

BibTeX
@InProceedings{pmlr-v310-hoang25a, title = {A lightweight and reliable framework toward real-time student engagement predictions in learning analytics}, author = {Hoang, Long and Shorten, George and O'Sullivan, Barry and Nguyen, Hoang D.}, booktitle = {Reliable and Trustworthy Artificial Intelligence 2025}, pages = {24--33}, year = {2025}, editor = {Nguyen, Hoang D. and Le, Duc-Trong and Björklund, Johanna and Vu, Xuan-Son}, volume = {310}, series = {Proceedings of Machine Learning Research}, month = {12 Dec}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v310/main/assets/hoang25a/hoang25a.pdf}, url = {https://proceedings.mlr.press/v310/hoang25a.html}, abstract = {Learning analytics can enable the provision of meaningful feedback based on the collected data, help educators to make decisions with and about learners, and improve learner performance. Student engagement predictions are a key factor in generating feedback for real-time learning analytics applications, such as dashboards. However, most previous work has been based on a heavy deep learning model, which results in challenges for deployment in real-time applications (a resource efficiency requirement in reliable AI). This paper proposes a lightweight deep-learning framework for predicting student engagement in video to address this limitation. The proposed method uses customized MobileNetV2 as the backbone, with an input size of 32 by 32 by 3, to extract features from consecutive video frames. Multi-Scale attention – Residual (MUSER) is used to capture global information and contextual representation of the extracted features. Finally, LSTM examines the temporal variations in video frames and yields the prediction result. We use the DAISEE dataset, the most popular dataset in the learning analytics community, to evaluate the proposed framework. Experimental results demonstrate that the proposed method achieves good accuracy while significantly reducing the model size compared to other approaches.} }
Endnote
%0 Conference Paper %T A lightweight and reliable framework toward real-time student engagement predictions in learning analytics %A Long Hoang %A George Shorten %A Barry O’Sullivan %A Hoang D. Nguyen %B Reliable and Trustworthy Artificial Intelligence 2025 %C Proceedings of Machine Learning Research %D 2025 %E Hoang D. Nguyen %E Duc-Trong Le %E Johanna Björklund %E Xuan-Son Vu %F pmlr-v310-hoang25a %I PMLR %P 24--33 %U https://proceedings.mlr.press/v310/hoang25a.html %V 310 %X Learning analytics can enable the provision of meaningful feedback based on the collected data, help educators to make decisions with and about learners, and improve learner performance. Student engagement predictions are a key factor in generating feedback for real-time learning analytics applications, such as dashboards. However, most previous work has been based on a heavy deep learning model, which results in challenges for deployment in real-time applications (a resource efficiency requirement in reliable AI). This paper proposes a lightweight deep-learning framework for predicting student engagement in video to address this limitation. The proposed method uses customized MobileNetV2 as the backbone, with an input size of 32 by 32 by 3, to extract features from consecutive video frames. Multi-Scale attention – Residual (MUSER) is used to capture global information and contextual representation of the extracted features. Finally, LSTM examines the temporal variations in video frames and yields the prediction result. We use the DAISEE dataset, the most popular dataset in the learning analytics community, to evaluate the proposed framework. Experimental results demonstrate that the proposed method achieves good accuracy while significantly reducing the model size compared to other approaches.
APA
Hoang, L., Shorten, G., O’Sullivan, B. & Nguyen, H.D.. (2025). A lightweight and reliable framework toward real-time student engagement predictions in learning analytics. Reliable and Trustworthy Artificial Intelligence 2025, in Proceedings of Machine Learning Research 310:24-33 Available from https://proceedings.mlr.press/v310/hoang25a.html.

Related Material