arbiter
JournalsPricingAccount

Facial emotion-based student's attention in online learning using deep learning

Swadha Gupta et al.

International Journal of Services Economics and Management2025https://doi.org/10.1504/ijsem.2025.148469article
AJG 1
Weight
0.37

What the paper says

Despite the growing popularity of online courses, it is still difficult to guarantee students' participation. Online students typically struggle to stay motivated and concentrated, in contrast to students in regular classrooms who benefit from direct supervision and motivation. Facial expression recognition is built into the framework so that the emotional state of the learner may be monitored and evaluated in real-time. To detect and evaluate student interest in the present moment, a deep learning-based strategy is proposed, incorporating deep learning models like VGG-19 and ResNet-50 for face expression identification. An attention index (AI) is determined through the analysis and classification of facial expressions, allowing for the forecasting of 'attentive' and 'inattentive' states. Accuracy is very high, with VGG-19 being the most accurate model at 93.11%. These results show the potential of deep learning as a tool for measuring and retaining students' interest.

1 citation

Open paper page →

Cite this paper

https://doi.org/https://doi.org/10.1504/ijsem.2025.148469

Or copy a formatted citation

@article{swadha2025,
  title        = {{Facial emotion-based student's attention in online learning using deep learning}},
  author       = {Swadha Gupta et al.},
  journal      = {International Journal of Services Economics and Management},
  year         = {2025},
  doi          = {https://doi.org/https://doi.org/10.1504/ijsem.2025.148469},
}

Paste directly into BibTeX, Zotero, or your reference manager.

Flag this paper

Facial emotion-based student's attention in online learning using deep learning

Flags are reviewed by the Arbiter methodology team within 5 business days.

Evidence weight

0.37

Balanced mode · F 0.40 / M 0.15 / V 0.05 / R 0.40

F · citation impact0.16 × 0.4 = 0.06
M · momentum0.53 × 0.15 = 0.08
V · venue signal0.50 × 0.05 = 0.03
R · text relevance †0.50 × 0.4 = 0.20

† Text relevance is estimated at 0.50 on the detail page — for your query’s actual relevance score, open this paper from a search result.