The Performance of Emotion Classifiers for Children With Parent-Reported Autism: Quantitative Feasibility Study
JMIR Mental Health2020Vol. 7(4), pp. e13174–e13174
Citations Over TimeTop 10% of 2020 papers
Haik Kalantarian, Khaled Jedoui, Kaitlyn Dunlap, Jessey Schwartz, Peter Washington, Arman Husic, Qandeel Tariq, Michael Ning, Aaron Kline, Dennis P. Wall
Abstract
The findings suggest that commercial emotion classifiers may be insufficiently trained for use in digital approaches to autism treatment and treatment tracking. Secure, privacy-preserving methods to increase labeled training data are needed to boost the models' performance before they can be used in AI-enabled approaches to social therapy of the kind that is common in autism treatments.
Related Papers
- → Which terms should be used to describe autism? Perspectives from the UK autism community(2015)1,797 cited
- → Brief Report: Learning About Autism: Is the Source of Autism Knowledge Associated with Differences in Autism Knowledge, Autism Identity, and Experiences of Stigma(2022)22 cited
- → Do Autism-Specific and General Developmental Screens Have Complementary Clinical Value?(2022)4 cited
- Susquehanna Chorale Spring Concert "Roots and Wings"(2017)
- → ИСПОЛЬЗОВAНИЕ ПОТЕНЦИAЛA СОЦИAЛЬНЫХ ПAРТНЕРОВ В ПОДГОТОВКЕ БУДУЩИХ ПЕДAГОГОВ(2024)