Blocking lower facial features reduces emotion identification accuracy in static faces and full body dynamic expressions
Bibliographic record
Abstract
During COVID, much of the world wore masks covering their lower faces to prevent the spread of disease. These masks cover lower facial features, but how vital are these lower facial features to the recognition of facial expressions of emotion? Going beyond the Ekman 6 emotions, in Study 1 (N = 372), we used a multilevel logistic regression to examine how artificially rendered masks influence emotion recognition from static photos of facial muscle configurations for many commonly experienced positive and negative emotions. On average, masks reduced emotion recognition accuracy by 17% percent for negative emotions and 23% for positive emotions. In Study 2 (N = 338), we asked whether these results generalised to multimodal full-body expressions of emotions, accompanied by vocal expressions. Participants viewed videos from a previously validated set, where the lower facial features were blurred from the nose down. Here, though the decreases in emotion recognition were noticeably less pronounced, highlighting the power of multimodal information, we did see important decreases for certain specific emotions and for positive emotions overall. Results are discussed in the context of the social and emotional consequences of compromised emotion recognition, as well as the unique facial features which accompany certain emotions.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.008 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.000 | 0.001 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.005 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".