Date
AI Overview
Why it matters
Mainstream digital interfaces are visually oriented, creating steep learning curves and frequent obstacles for screen reader users. Existing tutorials primarily target sighted users, while human assistance lacks real-time availability.
Study at a glance
- Question: Can an on-demand, context-aware AI assistant improve computer task completion and reduce workload for blind screen reader users?
- Setting and data: Remote study with 12 blind adult screen reader users evaluating Word and Excel tasks, plus 45 benchmark tasks.
- Method: Within-subject crossover experiment, benchmark evaluation, and semi-structured interviews
- AI tools: AskEase, OpenAI GPT-5, GPT-5-mini, text-embedding-3-large, GPT-4o, Gemma 3
Key findings
- Participants completed significantly more tasks using AskEase (1.5 of 2 tasks) than with baseline search or AI tools (0.5 tasks).
- AskEase significantly reduced participants' perceived physical demand, effort, and frustration while significantly improving perceived task performance.
- In robustness testing across 45 tasks from Windows Agent Arena, AskEase achieved an overall success rate of 96.6% with adaptive support.
Summary drafted with AI from the full paper and may contain errors. See the full paper for details.
Equal access to digital technologies is critical for education, employment, and social participation. However, mainstream interfaces are visually oriented, creating steep learning curves and frequent obstacles for screen reader users, and limiting their independence and opportunities. Existing support is inadequate -- tutorials mainly target sighted users, while human assistance lacks real-time availability. We introduce AskEase, an on-demand AI assistant that provides step-by-step, screen reader user-friendly guidance for computer use. AskEase manages multiple sources of context to infer user intent and deliver precise, situation-specific guidance. Its seamless interaction design minimizes disruption and reduces the effort of seeking help. We demonstrated its effectiveness through representative usage scenarios and robustness tests. In a within-subjects study with 12 screen reader users, AskEase significantly improved task success while reducing perceived workload, including physical demand, effort, and frustration. These results demonstrate the potential of LLM-powered assistants to promote accessible computing and expand opportunities for users with visual impairments.
Research Categories
What is the application?
Who is the user?
Who age?
Why use AI?
Study design
Methods
Datasets
Publication Source
Publisher
arXiv
