MatplotAlt is an open-source Python package for easily adding alternative text to matplotlib figures. MatplotAlt equips Jupyter notebook authors to automatically generate and surface chart descriptions with a single line of code or command, and supports a range of options that allow users to customize the generation and display of captions based on their preferences and accessibility needs.
Our evaluation indicates that MatplotAlt’s heuristic and LLM-based methods to generate alt text can create accurate long-form descriptions of both simple univariate and complex Matplotlib figures. We find that state-of-the-art LLMs still struggle with factual errors when describing charts, and improve the accuracy of our descriptions by prompting GPT4-turbo with heuristic-based alt text or data tables parsed from the Matplotlib figure.
Here is some example ALT text generated for the pie chart shown below. A variety of examples can be found in the MatPlotAlt documentation.
A pie chart titled ’percentage of annual sunshine’. There are 12 slices: jan (3.19%), feb (4.993%), mar (8.229%), apr (9.57%), may (11.7%), june (12.39%), july (14.42%), aug (12.99%), sep (10.22%), oct (6.565%), nov (3.329%), and dec (2.404%). The data has a standard deviation of x=4.006, an average of x=8.333, a maximum value of x=14.42, and a minimum value of x=2.404. The data strictly increase up to their max at x=14.42, then strictly decrease.
Telehealth and digital health innovations: A mixed landscape of access Phuong J, Ordóñez P, Cao J, Moukheiber M, Moukheiber L, et al. (2023) Telehealth and digital health innovations: A mixed landscape of access. PLOS Digital Health 2(12): e0000401. https://doi.org/10.1371/journal.pdig.0000401
In the wake of emergent natural and anthropogenic disasters, telehealth presents opportunities to improve access to healthcare when physical access is not possible. Yet, since the beginning of the COVID pandemic, lessons learned reveal that various populations in the United States do not or cannot adopt telehealth due to inequitable access. We explored the Digital Determinants of Health (DDoHs) for telehealth, characterizing the role of accessibility, broadband connectivity and electrical grids, and patient intersectionality. In addition to its role as an existing Social Determinant of Health, Policies and Laws directly and indirectly affect these DDoHs, making access more complex for marginalized populations. Digital systems lack the flexibility, accessibility, and usability to inclusively provide the essential services patients need in telehealth. We propose the following recommendations: (1) design technology and systems using accessibility and value sensitive design principles; (2) support a range of technologies and settings; (3) support multiple and diverse users; and (4) support clear paths for repair when technical systems fail to meet users’ needs. Addressing these requires change not only from providers but also from the institutions providing these systems.
Mobility aids (e.g., canes, crutches, and wheelchairs) are crucial for people with mobility disabilities; however, pervasive dissatisfaction with these aids keeps usage rates low. Through semi-structured interviews with 17 mobility aid users, mostly under the age of 30, we identified specific sources of dissatisfaction among younger users of mobility aids, uncovered community-based solutions for these dissatisfactions, and explored ways these younger users wanted to improve mobility aids. We found that users sought customizable, reconfigurable, multifunctional, and more aesthetically pleasing mobility aids. Participants’ feedback guided our prototyping of tools/accessories, such as laser cut decorative sleeves, hot-swappable physical interface modules, and modular canes with custom 3D-printed handles. These prototypes were then the focus of additional co-design sessions where six returning participants offered suggestions for improvements and provided feedback on their usefulness and usability. Our findings highlight that many mobility aid users have the desire, ability, and need to customize and improve their aids in different ways compared to older adults. We propose various solutions and design guidelines to facilitate the modifications of mobility aids.
Kate Glazko, JunHyeok Cha, Aaleyah Lewis, Ben Kosa, Brianna Wimer, Andrew Zheng, Yiwei Zheng, and Jennifer Mankoff. 2025. Autoethnographic Insights from Neurodivergent GAI “Power Users”. In CHI Conference on Human Factors in Computing Systems (CHI ’25), April 26-May 1, 2025, Yokohama, Japan. ACM, New York, NY, USA, 20 pages. https://doi.org/10.1145/ 3706598.3713670
Generative AI has become ubiquitous in both daily and professional life, with emerging research demonstrating its potential as a tool for accessibility. Neurodivergent people, often left out by existing accessibility technologies, develop their own ways of navigating normative expectations. GAI offers new opportunities for access, but it is important to understand how neurodivergent “power users”—successful early adopters—engage with it and the challenges they face. Further, we must understand how marginalization and intersectional identities influence their interactions with GAI. Our autoethnography, enhanced by privacy-preserving GAI-based diaries and interviews, reveals the intricacies of using GAI to navigate normative environments and expectations. Our findings demonstrate how GAI can both support and complicate tasks like code-switching, emotional regulation, and accessing information. We show that GAI can help neurodivergent users to reclaim their agency in systems that diminish their autonomy and self-determination. However, challenges such as balancing authentic self-expression with societal conformity, alongside other risks, create barriers to realizing GAI’s full potential for accessibility.
Aashaka Desai, Rahaf Alharbi, Stacy Hsueh, Richard E. Ladner, and Jennifer Mankoff. 2025. Toward Language Justice: Exploring Multilingual Captioning for Accessibility. In CHI Conference on Human Factors in Computing Systems (CHI ’25), April 26–May 01, 2025, Yokohama, Japan. ACM, New York, NY, USA, 18 pages. https://doi.org/10.1145/3706598.3713622
A growing body of research investigates how to make captioning experiences more accessible and enjoyable to disabled people. However, prior work has focused largely on English captioning, neglecting the majority of people who are multilingual (i.e., understand or express themselves in more than one language). To address this gap, we conducted semi-structured interviews and diary logs with 13 participants who used multilingual captions for accessibility. Our findings highlight the linguistic and cultural dimensions of captioning, detailing how language features (scripts and orthography) and the inclusion/negation of cultural context shape the accessibility of captions. Despite lack of quality and availability, participants emphasized the importance of multilingual captioning to learn a new language, build community, and preserve cultural heritage. Moving toward a future where all ways of communicating are celebrated, we present ways to orient captioning research to a language justice agenda that decenters English and engages with varied levels of fluency.
Glazko, K., Portnova-Fahreeva, A., Mankoff-Dey, A., Psarra, A., & Mankoff, J. (2024, July). Shaping Lace: Machine embroidered metamaterials. In Proceedings of the 9th ACM Symposium on Computational Fabrication (pp. 1-12).
The ability to easily create embroidered lace textile objects that can be manipulated in structured ways, i.e., metamaterials, could enable a variety of applications from interactive tactile graphics to physical therapy devices. However, while machine embroidery has been used to create sensors and digitally enhanced fabrics, its use for creating metamaterials is an understudied area. This article reviews recent advances in metamaterial textiles and conducts a design space exploration of metamaterial freestanding lace embroidery. We demonstrate that freestanding lace embroidery can be used to create out-of-plane kirigami and auxetic effects. We provide examples of applications of these effects to create a variety of prototypes and demonstrations.
As Generative AI rises in adoption, its use has expanded to include domains such as hiring and recruiting. However, without examining the potential of bias, this may negatively impact marginalized populations, including people with disabilities. To address this important concern, we present a resume audit study, in which we ask ChatGPT (specifically, GPT-4) to rank a resume against the same resume enhanced with an additional leadership award, scholarship, panel presentation, and membership that are disability-related. We find that GPT-4 exhibits prejudice towards these enhanced CVs. Further, we show that this prejudice can be quantifiably reduced by training a custom GPTs on principles of DEI and disability justice. Our study also includes a unique qualitative analysis of the types of direct and indirect ableism GPT-4 uses to justify its biased decisions and suggest directions for additional bias mitigation work. Additionally, since these justifications are presumably drawn from training data containing real-world biased statements made by humans, our analysis suggests additional avenues for understanding and addressing human bias.
Storing, organizing, and decorating are key parts of making a home nice. Buying new things for these tasks can be expensive, and reuse is better for the planet. One way to do this is with a “home hack.” This is when you use things you already have at home to solve a problem. But creating these hacks can be hard, especially if they are big, need to be nailed or screwed to the wall.
We have a system called FabHacks to help make these home hacks easier to create. It uses a new, hack-specific language we made called FabHaL to help you build these hacks. We looked at home hacks people share online and found ways to connect household items using specific methods. We also have a simple app to help you design such hacks. FabHacks, is based on a solver-aided domain-specific language (S-DSL). It leverages a physics-based solver that finds the expected physical configuration of a hack. We tested FabHacks by having people use our system, and they could easily make and try different designs.
Computational notebooks are tools that help people explore, analyze data, and create stories about that data. They are the most popular choice for data scientists. People use software like Jupyter, Datalore, and Google Colab to work with these notebooks in universities and companies.
There is a lot of research on how data scientists use these notebooks and how to help them work together better. But there is not much information about the problems faced by blind and visually impaired (BVI) users. BVI users have difficulty using these notebooks because:
The interfaces are not accessible.
The way data is shown is not user-friendly for them.
Popular libraries do not provide outputs they can use.
We analyzed 100,000 Jupyter notebooks to find accessibility problems. We looked for issues that affect how these notebooks are created and read. From our study, we give advice on how to make notebooks more accessible. We suggest ways for people to write better notebooks and changes to make the notebook software work better for everyone.
Ather Sharif, Venkatesh Potluri, Jazz Rui Xia Ang, Jacob O. Wobbrock, Jennifer Mankoff: Touchpad Mapper: Examining Information Consumption From 2D Digital Content Using Touchpads by Screen-Reader Users: ASSETS ’24 (best poster!) and W4A ’24 (open access)
Touchpads are common, but they are not very useful for people who use screen readers. We created and tested a tool called Touchpad Mapper to let Blind and visually impaired people make better use of touchpads. Touchpad Mapper lets screen-reader users use touchpads to interact with digital content like images and videos.
Touchpad mapping could be used in many apps. We built two examples:
Users can use the touchpad to identify where things are in an image.
Users can control a video’s progress with the touchpad, including rewinding and fast-forwarding.
We tested Touchpad Mapper with three people who use screen readers. They said they got information more quickly with our tool than with a regular keyboard.
