Comparing three algorithms of automated facial expression analysis in autistic children: different sensitivities but consistent proportions
Commonly used automated facial analysis algorithms exhibit large variability in their output when identifying facial expressions of young children during naturalistic social interactions. Nonetheless, all three algorithms did not identify differences in the quantity of facial expressions across groups, suggesting that atypical production of facial expressions in verbal children with autism is likely related to their quality, timing, and social context rather than their quantity during natural social interaction.
Authors
- Liora Manelis‐Baram (ORCID: https://orcid.org/0000-0003-0616-2724)
- Carmel Sofer (ORCID: https://orcid.org/0000-0001-8871-5112)
- Michal Ilan (ORCID: https://orcid.org/0000-0002-8774-3231)
- Idan Menashe
- Ilan Dinstein (ORCID: https://orcid.org/0000-0001-8106-5209)
- Gal Meiri (ORCID: https://orcid.org/0000-0003-4100-4588)
- Tal Barami (ORCID: https://orcid.org/0000-0002-1554-2289)
- Elizabeth Soskin
Institutions
- Ben-Gurion University of the Negev (IL)
- Soroka Medical Center (IL)
Publication Details
- Journal
- Molecular Autism
- Published
- 2025-10-09
- DOI
- https://doi.org/10.1186/s13229-025-00685-x
- Citations
- 2
- Primary Topic
- Autism Spectrum Disorder Research
- Type
- article
- Field-Weighted Citation Impact
- 2.86
Funders
- Israel Science Foundation
- Azrieli Foundation