Lessons Learned in Designing AI for Autistic Adults
Abstract
Through an iterative design process using Wizard of Oz (WOz) prototypes, we designed a video calling application for people with Autism Spectrum Disorder. Our Video Calling for Autism prototype provided an Expressiveness Mirror that gave feedback to autistic people on how their facial expressions might be interpreted by their neurotypical conversation partners. This feedback was in the form of emojis representing six emotions and a bar indicating the amount of overall expressiveness demonstrated by the user. However, when we built a working prototype and conducted a user study with autistic participants, their negative feedback caused us to reconsider how our design process led to a prototype that they did not find useful. We reflect on the design challenges around developing AI technology for an autistic user population, how Wizard of Oz prototypes can be overly optimistic in representing AI-driven prototypes, how autistic research participants can respond differently to user experience prototypes of varying fidelity, and how designing for people with diverse abilities needs to include that population in the development process.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
GenAI is very useful for autistic individuals who use GenAI to formulate emails, deal with conflicts, prepare for conversations with supervisors and colleagues, and even when trying to understand their own and others' emotions.
“It is also very useful for autistic individuals who use GenAI to formulate emails, deal with conflicts, prepare for conversations with supervisors and colleagues, and even when trying to understand their own and others' emotions [14, 15, 16, 17].”
Many traditional accessibility tasks inherently involve ambiguity and subjective interpretation, such as sign language translation and emotion recognition.
“Similar to stuttering, many traditional accessibility tasks inherently involve ambiguity and subjective interpretation, such as sign language translation [12] and emotion recognition [8].”
From Disability-First AI Dataset Annotation: Co-designing Stuttered Speech Annotation Guidelines with People Who Stutter (2026) · cites this paper as [8]
Cites
Re-examining Whether, Why, and How Human-AI Interaction Is Uniquely Difficult to Design
Yang, Q., Steinfeld, A., Rosé, C., & Zimmerman, J. (2020) · Proceedings of the 2020 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3313831.3376301 · Cited by 622 · see citing works
Managing Stress: The Needs of Autistic Adults in Video Calling
Zolyomi, A., Begel, A., Waldern, J. F., Tang, J., Barnett, M., Cutrell, E., McDuff, D., Andrist, S., & Morris, M. R. (2019) · Proceedings of the ACM on Human-Computer Interaction · doi:10.1145/3359236 · Cited by 101 · see citing works
Self-citationUsage of Subjective Scales in Accessibility Research
Trewin, S., Marques, D., & Guerreiro, T. (2015) · Proceedings of the 17th International ACM SIGACCESS Conference on Computers & Accessibility - ASSETS '15 · doi:10.1145/2700648.2809867 · Cited by 35 · see citing works
Flagged first, then by citations
Cited by
Sorted by citations
Question-Driven Design Process for Explainable AI User Experiences
Liao, Q. V., Pribić, M., Han, J., Miller, S., & Sow, D. (2021) · arXiv · doi:10.48550/arxiv.2104.03483 · Cited by 18 · see citing works
Tang, X., Li, J., & Wu, S. (2026) · Proceedings of the 2026 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3772318.3790405 · Cited by 4 · see citing works
“Similar to stuttering, many traditional accessibility tasks inherently involve ambiguity and subjective interpretation, such as sign language translation [12] and emotion recognition [8].”
Matulewski, J., Sikorski, Ł., & Baczała, D. (2026) · Proceedings of the 63rd ACM Conference on Computers and People Research · doi:10.1145/3768310.3807803
- Authors
- Begel, A., Tang, J., Andrist, S., Barnett, M., Carbary, T., Choudhury, P., Cutrell, E., Fung, A., Junuzovic, S., McDuff, D., Rowan, K., Sahoo, S., Waldern, J. F., Wolk, J., Zheng, H., & Zolyomi, A.
- Affiliations
- Microsoft (United States) (US)
- University of Houston (US)
- Umeå University (SE)
- George Mason University (US)
- University of Washington (US)
- ORCID
- Venue
- Proceedings of the 22nd International ACM SIGACCESS Conference on Computers and Accessibility
- Publisher
- ACM
- Published
- 2020-10-26
- Pages
- 1-6
- OpenAlex
- W3081183526
- Cited by
- 34
- References
- 3
- Citations by year
- 2026: 4 · 2025: 9 · 2024: 9 · 2023: 6 · 2022: 3 · 2021: 3
- FWCI
- 2.19
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- International ACM SIGACCESS Conference on Computers and Accessibility (ASSETS) (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Human-Computer Interaction › Innovative Human-Technology Interaction
- Physical Sciences › Computer Science › Human-Computer Interaction › Usability and User Interface Design
- Social Sciences › Psychology › Social Psychology › Social Robot Interaction and HRI
- Keywords
- autism spectrum disorder, autistic adults, prototype fidelity, user experience design, inclusive design, assistive technology
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
