Lessons Learned in Designing AI for Autistic Adults

Begel, Andrew; Tang, John C.; Andrist, Sean; Barnett, Michael D.; Carbary, Tony; Choudhury, Piali; Cutrell, Edward; Fung, Alberto; Junuzovic, Sasa; McDuff, Daniel; Rowan, Kael; Sahoo, Shibashankar; Waldern, Jennifer Frances; Wolk, Jessica; Zheng, Hui; Zolyomi, Annuska

doi:10.1145/3373625.3418305

Cited by 15 publications

(5 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Other design challenges of AI UX discussed in the literature include a shift towards data-driven design culture [17,36], challenges to prototype and engage in quick design iterations [13,50,53,59], and the needs to engage stakeholders to align the values of AI system [38,60]. Our work will primarily tackle supporting a "designerly" understanding on the technical space of XAI, and designer-AI engineer collaboration, as discussed in the requirements below.…”

Section: Ioutputmentioning

confidence: 99%

Questioning the AI: Informing Design Practices for Explainable AI User Experiences

Liao

Gruen

Miller

2020

Proceedings of the 2020 CHI Conference on Human Factors in Computing Systems

451

202

View full text Add to dashboard Cite

A pervasive design issue of AI systems is their explainability-how to provide appropriate information to help users understand the AI.The technical field of explainable AI (XAI) has produced a rich toolbox of techniques. Designers are now tasked with the challenges of how to select the most suitable XAI techniques and translate them into UX solutions. Informed by our previous work studying design challenges around XAI UX, this work proposes a design process to tackle these challenges. We review our and related prior work to identify requirements that the process should fulfill, and accordingly, propose a Question-Driven Design Process that grounds the user needs, choices of XAI techniques, design, and evaluation of XAI UX all in the user questions. We provide a mapping guide between prototypical user questions and exemplars of XAI techniques, serving as boundary objects to support collaboration between designers and AI engineers. We demonstrate it with a use case of designing XAI for healthcare adverse events prediction, and discuss lessons learned for tackling design challenges of AI systems.CCS Concepts: • Human-centered computing → Interaction design process and methods; • Computing methodologies → Artificial intelligence.

show abstract

Section: Ioutputmentioning

confidence: 99%

Questioning the AI: Informing Design Practices for Explainable AI User Experiences

Liao

Gruen

Miller

2020

Proceedings of the 2020 CHI Conference on Human Factors in Computing Systems

451

202

View full text Add to dashboard Cite

show abstract

“…In supporting such individual tasks, there can be several AI-driven automation and facilitation features, such as an LLM-based executive functioning manager who can help list up the tasks and recommend priority tasks, a generative-AI driven resume builder, a mock-up interview agent who can synchronously generate new questions and give realtime suggestions to people with autism, interactive reader agent that receives the job call and enable interactive Q & A to reduce the reading amount for people with autism, and many more. Although AI can provide a reasonable initial material to work on, adding humans-including people with autism and their collaborators-in the loop can add a much-needed personal touch to tailor these responses more specifically to job seekers' needs as per current state-of-the-art in human-AI collaboration studies [9,87].…”

Section: Implications For Future Designmentioning

confidence: 99%

Collaborative Job Seeking for People with Autism: Challenges and Design Opportunities

Ara,

Ganguly,

Peppard

et al. 2024

Proceedings of the CHI Conference on Human Factors in Computing Systems

View full text Add to dashboard Cite

Successful job search results from job seekers' well-shaped social communication. While well-known differences in communication exist between people with autism and neurotypicals, little is known about how people with autism collaborate with their social surroundings to strive in the job market. To better understand the practices and challenges of collaborative job seeking for people with autism, we interviewed 20 participants including applicants with autism, their social surroundings, and career experts. Through the interviews, we identified social challenges that people with autism face during their job seeking; the social support they leverage to be successful; and the technological limitations that hinder their collaboration. We designed four probes that represent major collaborative features found from the interviews-executive planning, communication, stage-wise preparation, and neurodivergent community formation-and discussed their potential usefulness and impact through three focus groups. We provide implications regarding how our findings can enhance collaborative job seeking experiences for people with autism through new designs. CCS Concepts• Human-centered computing → Empirical studies in collaborative and social computing; Collaborative and social computing systems and tools; Empirical studies in accessibility; Accessibility systems and tools.

show abstract

“…However, both these studies and additional research [5,23] show that simulating ML models behaviors in WoZ is no easy task. Among the challenges identified is the difficulty to realistically reproduce ML errors, because they are unlike human errors [3,26]. For instance, Riek [19] shows that only 3.7% of the WoZ studies in the Human-Robot Interaction domain include deliberate errors.…”

mentioning

confidence: 99%

“…For instance, Riek [19] shows that only 3.7% of the WoZ studies in the Human-Robot Interaction domain include deliberate errors. ML errors are an intrinsic feature of ML models, and omitting them in a WoZ can lead to findings that are not representative of the user experience that is being simulated [3].…”

mentioning

confidence: 99%

Wizard of Errors: Introducing and Evaluating Machine Learning Errors in Wizard of Oz Studies

Jansen

Colombo

2022

CHI Conference on Human Factors in Computing Systems Extended Abstracts

View full text Add to dashboard Cite

When designing Machine Learning (ML) enabled solutions, designers often need to simulate ML behavior through the Wizard of Oz (WoZ) approach to test the user experience before the ML model is available. Although reproducing ML errors is essential for having a good representation, they are rarely considered. We introduce Wizard of Errors (WoE), a tool for conducting WoZ studies on MLenabled solutions that allows simulating ML errors during user experience assessment. We explored how this system can be used to simulate the behavior of a computer vision model. We tested WoE with design students to determine the importance of considering ML errors in design, the relevance of using descriptive error types instead of confusion matrix, and the suitability of manual error control in WoZ studies. Our work identifies several challenges, which prevent realistic error representation by designers in such studies. We discuss the implications of these findings for design. CCS CONCEPTS• Human-centered computing → User studies; Interactive systems and tools; Systems and tools for interaction design.

show abstract

Lessons Learned in Designing AI for Autistic Adults

Cited by 15 publications

References 20 publications

Questioning the AI: Informing Design Practices for Explainable AI User Experiences

Questioning the AI: Informing Design Practices for Explainable AI User Experiences

Collaborative Job Seeking for People with Autism: Challenges and Design Opportunities

Wizard of Errors: Introducing and Evaluating Machine Learning Errors in Wizard of Oz Studies

Contact Info

Product

Resources

About