Online learning environments provide rich digital traces of learner activity, yet they offer limited access to the non-verbal affective cues that instructors naturally observe in face-to-face classrooms. This study investigates facial expression analysis as an affective sensing component for emotion-aware online learning.
Facial data were collected from 26 students during online learning sessions, and self-reported emotion labels were mapped into three affective categories: positive, neutral and negative. The visual stream was transformed into standardized face-centered representations and evaluated using a lightweight CNN implementation together with representative pretrained CNN architectures.
The results show that facial expressions are perceived by participants as meaningful non-verbal cues in online learning. In the classification experiments, VGG19 achieved the highest accuracy (0.79), while the lightweight CNN achieved a comparable accuracy (0.78) with the lowest loss value.
These findings suggest that facial-expression-based affective cues can be extracted from online learning data and may complement conventional learning analytics in future emotion-aware educational systems.
Reframes facial expression recognition as an affective sensing problem for emotion-aware online learning.
Proposes a label-informed pipeline linking self-reported learner emotions with facial-expression-based affective cues.
Provides an end-to-end framework for processing authentic webcam data collected during online learning sessions.
Shows that lightweight and pretrained CNN models can extract broad affective cues under a unified three-class taxonomy.
