Manuscript received August 29, 2025; revised October 23, 2025; accepted April 22, 2026; published October 22, 2026.

Abstract—In online learning settings, the instructor is usually not able to monitor the non-verbal behavior of students in terms of body language and facial orientation, which could be used to tell whether the student is paying attention or not. This paper examines how machine learning can be used to categorize visual cues of body language that can be used to predict attentiveness in students during online learning. The face-pose image dataset was publicly available and obtained through Kaggle and consisted of around 2000 images and served as a proxy dataset of attention-related visual behavior. Image classification was performed using four machine learning models: Support Vector Machine (SVM), Decision Tree (DT), Random Forest (RF), and Convolutional Neural Network (CNN). The images all underwent preprocessing of resizing to a 48 × 48-pixel grayscale to have a consistent input representation. The experimental results indicate that the SVM model achieved the highest classification accuracy of 95%, followed by DT (89%), RF (85%), and CNN (72%). The results indicate that machine learning models have the potential to be effective in classifying body-orientation cues based on image data and can be used to build future systems that will analyze student engagement in online learning environments.

Keywords—online learning, body language, student behavior prediction, student engagement detection, machine learning, image classification
 

Cite: Rawad Abdulghafor, "Prediction of Students' Behavior in Online Learning through Body Language Using Machine Learning," Journal of Image and Graphics, Vol. 14, No. 5, pp. 902-909, 2026.

Copyright © 2026 by the authors. This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited (CC BY 4.0).