Blending Human and Artificial Intelligence to Support Autistic Children’s Social Communication Skills
- Submitting institution
-
University of Dundee
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 34181634
- Type
- D - Journal article
- DOI
-
10.1145/3271484
- Title of journal
- ACM Transactions on Computer-Human Interaction
- Article number
- 35
- First page
- -
- Volume
- 25
- Issue
- 6
- ISSN
- 1073-0516
- Open access status
- Compliant
- Month of publication
- December
- Year of publication
- 2018
- URL
-
-
- Supplementary information
-
-
- Request cross-referral to
- -
- Output has been delayed by COVID-19
- No
- COVID-19 affected output statement
- -
- Forensic science
- No
- Criminology
- No
- Interdisciplinary
- No
- Number of additional authors
-
18
- Research group(s)
-
-
- Citation count
- 7
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- This paper reports a UK-wide multi-site study evaluating an adaptive AI-based learning environment for children with autism spectrum conditions (ASC). It describes a replicable mixed-methods study design for technology interventions with hard-to-reach heterogeneous populations, demonstrating an alternative to traditional single case study approaches by standardizing data collection and analysis. Dundee managed two sites (12 participants), reporting data from 5 severe ASC participants (n=15). The use of formalised video analysis has underpinned mixed-methods evaluation of AAC projects with heterogeneous users, e.g., the EPSRC-funded ACE-LP project, and contributed to Waller’s Honorary Fellowship of the Royal College of Speech and Language Therapists.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -