Facial expression recognition of six basic emotions via FACS can detect learner emotional states in real time¶

Claim · All claims
Evidence · 1 study · associational r1 · q2
Currency · newest study 2024 · not yet checked against its sources · not reviewed by a person

Subclaims¶

q2 i? FACS-based tools distinguish six basic emotional states with high reported accuracy. → Hayashi 2024

Evidence¶

Hayashi 2024¶

Hayashi, Y. (2024). Modeling Synchronization for Detecting Collaborative Learning Process Using a Pedagogical Conversational Agent: Investigation Using Recurrent Indicators of Gaze, Language, and Facial Expression. International Journal of Artificial Intelligence in Education. https://doi.org/10.1007/s40593-023-00381-y

q2 · i? · associational · r1

Narrative review reporting the Face Reader software's stated 89% accuracy for six basic emotions; the article interprets the six emotions as markers of collaborative states such as joy at consensus or sadness when a concept is hard to understand.

"Face Reader (van Kuilenburg et al., 2005) utilizes FACS to distinguish between the six basic emotional states with 89% accuracy."

Discussion¶

Related Claims¶

• MathBuddy's multimodal emotion aggregation matched participant-reviewed emotions at 60% overall accuracy, with sharply reduced recall for the Neutral class — related
• Detection-oriented emotion AI faces contextual under-interpretation: emotional signals lack stable meanings independent of person, task, culture, and situation — reports the opposite
• In a within-subject user study, participants showed longer positive facial expressions under the emotion-aware (Emotion ON) tutoring condition — related
• Recurrence indicators (gaze, lexical, emotional) predicted collaborative learning process measures but not learning performance — related