Intelligent emotion and behavior recognition for online learners using deep affective computing
Priya K, Pradeep G, Ravimaran S · 2026
Read Intelligent emotion and behavior recognition for online learners using deep affective computing by Priya K, Pradeep G, Ravimaran S (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-13478150.txt.
Description
Priya and co-authors describe a system in 2026 that reads online students' faces by webcam to judge both emotion and engagement during live classes. Teachers in video classes cannot easily see confusion or frustration, so the system watches for them. It detects faces frame by frame, encodes them with a neural network that attends to informative regions, then tracks 16-frame clips to classify each learner as engaged, confused, frustrated, or disengaged.
On the standard FER2013 emotion benchmark, the model scored 94.5 percent accuracy on the private test split used for final ranking. On behavior data from 120 learners covering 800 labeled clips, it reached 86.9 percent accuracy across the four learning states tested. The full pipeline ran at about 25 frames per second on mid-range graphics hardware, fast enough for live monitoring, and it beat systems using facial expressions alone.
Catalog record
| CREATOR | Priya K, Pradeep G, Ravimaran S |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 106 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |