Enhancing comprehensibility of social media for blind people using generative AI - the overarching goal of this three-year project led by michigan state university in collaboration with old dominion…

Active Grant Awarded

Award ID
90IFRE0117
Recipient
Awarding agency
Obligated
$248,425

Award facts

Completion date 5% complete
Place of performance
East Lansing, MI, USA

Award details come from USAspending.gov.

About this award

The Department of Health and Human Services Administration for Community Living awarded Grant 90IFRE0117 to Michigan State University on Sep 23, 2026, with $248,425 obligated. The award falls under CFDA 93.433, ACL National Institute on Disability, Independent Living, and Rehabilitation Research. The funding agency record also lists the National Institute on Disability Independent Living and Rehabilitation Research as an alternate name.

The three-year project addresses how people who are blind or visually impaired can comprehend and engage with noisy user-generated social media content that is poorly suited to screen-reader listening. Michigan State leads the work in collaboration with Old Dominion University. Prototype interview studies will show participants large language model-driven mock-ups to surface their needs and preferences on vocalizing posts and explicitly contextualizing them.

Deliverables are mock-up prototypes demonstrating different vocalization and contextualization strategies, design guidelines for audio interfaces on how to voice social-media content for blind and visually impaired users, and design guidelines for intelligent assistive technology specifying the type and length of contextual information to append to posts. The ultimate completion date is Sep 29, 2029, and place of performance is East Lansing, Michigan.

Description

Enhancing comprehensibility of social media for blind people using generative AI - the overarching goal of this three-year project led by michigan state university in collaboration with old dominion university is to help people who are blind or visual impaired (BVI) easily comprehend and engage with noisy user-generated content on social media that is often not suitable for listening-based interaction with a screen reader. In pursuit of this goal, the objectives are: (I) uncovering the needs and preferences of BVI users regarding vocalization of user-generated social-media content; and (II) identifying the needs and preferences of BVI users regarding explicit contextualization of social-media posts. To fulfill these objectives, prototype interview studies will be conducted where large language model-driven mock-UPS will be showcased to the study participants, to help them better express their needs and preferences. The outcomes include: (I) assistive technology developers will have clear guidelines on how to design or update their products for improving accessibility of user-generated content in applications; and (II) state-of-the-art generative-AI technology will be increasingly employed for devising new and effective accessibility-enhancing solutions for social media and beyond. The expected products are: (I) mock-up prototypes demonstrating different vocalization and contextualization strategies for user-generated social-media content; II) design guidelines for audio-interfaces, recommending how to voice out social-media content for BVI users; and (III) design guidelines for intelligent assistive technology, suggesting the type and length of contextual information to be appended to the social-media posts for improving their comprehensibility to BVI users.

Quick answers

Who received award 90IFRE0117?

90IFRE0117 was awarded to Michigan State University by National Institute on Disability Independent Living and Rehabilitation Research (Administration for Community Living) on September 23, 2026.

How much is award 90IFRE0117 worth?

$248,425 has been obligated on 90IFRE0117.

On GovTribe

See this award's full record

  • Every transaction and subaward
  • The recipient's other awards and teaming partners
  • Similar grant awards
  • Ask GovTribe AI about this award