About

JooYoung Seo is an Assistant Professor in the Information Sciences at the Siebel School of Computing and Data Science, University of Illinois Urbana-Champaign. His recent courses include Research Design, Introduction to Human-Computer Interaction, Introduction to Data Science, and Accessibility in Human-Computer Interaction. His research focuses on various aspects of computing and data science, contributing to the development of innovative approaches in these fields. As a faculty member, he is involved in teaching, research, and service within the school, supporting the advancement of computing and data science education and research.

Research topics

• Computer Science
• Information Retrieval
• Data Mining
• Data science
• Political Science
• Multimedia
• Family medicine
• World Wide Web
• Psychiatry
• Optometry
• Medicine
• Psychology
• Library science
• Human–computer interaction
• Statistics
• Mathematics
• Pathology

Selected publications

• Py maidr: Bridging Visual and Non-Visual Data Experiences Through a Unified Python Framework

  ArXiv.org · 2025-09-16

  preprintOpen access1st authorCorresponding

  Although recent efforts have developed accessible data visualization tools for blind and low-vision (BLV) users, most follow a "design for them" approach that creates an unintentional divide between sighted creators and BLV consumers. This unidirectional paradigm perpetuates a power dynamic where sighted creators produce non-visual content boundaries for BLV consumers to access. This paper proposes a bidirectional approach, "design for us," where both sighted and BLV collaborators can employ the same tool to create, interpret, and communicate data visualizations for each other. We introduce Py maidr, a Python package that seamlessly encodes multimodal (e.g., tactile, auditory, conversational) data representations into visual plots generated by Matplotlib and Seaborn. By simply importing the maidr package and invoking the maidr.show() method, users can generate accessible plots with minimal changes to their existing codebase regardless of their visual dis/abilities. Our technical case studies demonstrate how this tool is scalable and can be integrated into interactive computing (e.g., Jupyter Notebook, Google Colab), reproducible and literate programming (e.g., Quarto), and reactive dashboards (e.g., Shiny, Streamlit). Our performance benchmarks demonstrate that Py maidr introduces minimal and consistent overhead during the rendering and export of plots against Matplotlib and Seaborn baselines. This work significantly contributes to narrowing the accessibility gap in data visualization by providing a unified framework that fosters collaboration and communication between sighted and BLV individuals.

  PublisherOA PDFDOI

• Check Now, Can You See It?: Exploring Voice and Video-Capable Language Models for Identifying and Spatially Locating Items of Interest for Blind and Low-Vision Travelers

  2025-10-22 · 1 citations

  articleOpen accessSenior author
  PublisherOA PDFDOI

• Phoenix: A Novel Context-Aware Voice-Powered Math Equation Workspace and Editor

  2025-10-22

  articleOpen accessSenior author

  Writing mathematical notation requires substantial effort, diverting cognitive resources from conceptual understanding to documentation mechanics, significantly impacting individuals with fine motor disabilities (FMDs). Current limits of speech-based math technologies rely on precise dictation of math symbols and unintuitive command-based interfaces. We present a novel voice-powered math workspace, applying neuroscience insights to create an intuitive problem-solving environment. To minimize cognitive load, we leverage large language models with our novel context engine to support natural language interaction. Ultimately, we enable fluid mathematical engagement for individuals with FMDs -- freed from mechanical constraints.

  PublisherOA PDFDOI

• Sensing the Shape of Data: Non-Visual Exploration of Statistical Concepts in Histograms with Blind and Low-Vision Learners

  ArXiv.org · 2025-09-17

  preprintOpen accessSenior author

  Statistical concepts often rely heavily on visual cues for comprehension, presenting challenges for individuals who face difficulties using visual information, such as the blind and low-vision (BLV) community. While prior work has explored making data visualizations accessible, limited research examines how BLV individuals conceptualize and learn the underlying statistical concepts these visualizations represent. To better understand BLV individuals' learning strategies for potentially unfamiliar statistical concepts, we conducted a within-subjects experiment with 7 BLV individuals, controlling for vision condition using blindfolds. Each participant leveraged three different non-visual representations (Swell Touch tactile graph (STGs), shaped data patterns on a refreshable display (BDPs), sonification) to understand three different statistical concepts in histograms (skewness, modality, kurtosis). We collected quantitative metrics (accuracy, completion time, self-reported confidence levels) and qualitative insights (gesture analysis) to identify participants' unique meaning-making strategies. Results revealed that the braille condition led to the most accurate results, with sonification tasks being completed the fastest. Participants demonstrated various adaptive techniques when exploring each histogram, often developing alternative mental models that helped them non-visually encode statistical visualization concepts. Our findings reveal important implications for statistics educators and assistive technology designers, suggesting that effective learning tools must go beyond simple translation of visual information to support the unique cognitive strategies employed by BLV learners.

  PublisherOA PDFDOI

• "Sighted People Have Their Pick Of The Litter": Unpacking The Need For Digital Mental Health (DMH) Tracking Services With And For The Blind Community

  2025-04-23 · 2 citations

  articleOpen accessSenior author

  The proliferation of digital mental health (DMH) tracking services promises personalized support, yet accessibility barriers limit equal access. This study investigates blind community experiences with DMH tracking services across the United States as a step toward inclusive health technology design. Working with blind advocacy organizations, we distributed a cross-sectional observational survey (n = 93) and analyzed open-ended responses using Norman and Skinner's eHealth Literacy framework. Our findings reveal significant challenges in navigation, content interpretation, and overall user experience, which impede the blind community's effective engagement with DMH tools. Results highlight the need for adaptive interfaces, accessible tracking strategies, and voice-guided interactions. These insights inform design recommendations for developers and policymakers, promoting more inclusive mental health technologies. By prioritizing accessibility, we make forward progress in ensuring that DMH tracking services fulfill their potential to support mental well-being across diverse user groups, fostering digital equality in mental health care.

  PublisherOA PDFDOI

• Explore, Listen, Inspect: Supporting Multimodal Interaction with 3D Surface and Point Data Visualizations

  2025-10-22 · 1 citations

  articleOpen accessSenior author

  Blind and low-vision (BLV) users remain largely excluded from three-dimensional (3D) surface and point data visualizations due to the reliance on visual interaction. Existing approaches inadequately support non-visual access, especially in browser-based environments. This study introduces DIXTRAL, a hosted web-native system, co-designed with BLV researchers to address these gaps through multimodal interaction. Conducted with two blind and one sighted researcher, this study took place over sustained design sessions. Data were gathered through iterative testing of the prototype, collecting feedback on spatial navigation, sonification, and usability. Co-design observations demonstrate that synchronized auditory, visual, and textual feedback, combined with keyboard and gamepad navigation, enhances both structure discovery and orientation. DIXTRAL aims to improve access to 3D continuous scalar fields for BLV users and inform best practices for creating inclusive 3D visualizations.

  PublisherOA PDFDOI

• Development of a personalized conversational health agent to enhance physical activity for blind and low-vision individuals

  mHealth · 2025-07-01 · 2 citations

  articleOpen access

  Background: With the advancements in mobile health (mHealth) technologies, sighted individuals can benefit from mobile apps and wearable devices to more easily manage their physical activity (PA) and wellness data through intuitive touch gestures and effective data visualizations. However, for blind and low-vision (BLV) individuals, these conventional interaction methods are often challenging, not only limiting their ability to use these technologies but also potentially diminishing their motivation to adopt them to support health-promoting behaviors. We aimed to develop a health monitoring application called Personalized and Conversational Health Agent (PCHA) that supports BLV individuals with self-monitoring and management of their PA and wellness data (e.g., step count, exercise duration, calories burned, heart rate). Methods: Drawing on social cognitive theory and insights from prior needs assessment research, five key design goals were established to guide the development of the app's core features and functionalities. PCHA leverages a large language model (LLM) to enable a conversational health agent that can be installed on iPhone and Apple Watch devices. This conversational interface is designed to ensure accessibility and inclusivity, offering PA management tools through a voice user interface (VUI) that minimizes the navigation challenges often associated with traditional touchscreen-based systems. To ensure evidence-based PA guidance, a thorough review of scientific literature and published PA guidelines was conducted. Finally, two blind accessibility experts conducted the accessibility testing. Results: Accessible user interface (UI) designs, featuring high color contrast, large buttons, and a simple layout, were created using Figma. The main features and functionalities include: (I) a voice health interview to assess users' basic health information; (II) PA recommendations to guide users toward achieving their PA goals; (III) a chat feature enabling human-like conversations with the app; (IV) a PA scheduling and reminder feature with haptic feedback on the Apple Watch; and (V) an in-exercise mode that provides audible updates on heart rate, PA duration, and walking speed. The app's mobile accessibility was found to be satisfactory. Conclusions: A follow-up study involving BLV research participants will be conducted to improve the app's accessibility and usability, and to update its features and functionalities. More research is needed to fully harness the potential of LLMs in the new mHealth system to motivate PA behaviors for BLV populations. To deliver truly personalized PA feedback for BLV individuals, mHealth app developer should incorporate PA and wellness data specific to the BLV population, along with their unique personal and contextual factors that influence PA behaviors.

  PublisherDOI

• Engaging with information beyond vision: hands-on approaches to computational thinking for blind and visually impaired learners

  Information Research an international electronic journal · 2025-03-11

  articleOpen access

  Introduction: This project develops accessible maker tools and activities to foster computational thinking (CT) skills in blind and visually impaired (BVI) learners, while investigating the experiences of two key groups: (1) BVI learners and (2) librarians and maker professionals who design and deliver accessible CT programs. Methods: The pilot phase designed and delivered an accessible electronics and coding curriculum to three BVI youth in a two-day summer camp. Data was collected through two debrief focus groups—one with BVI learners and one with the maker professionals who served as instructors. Analysis: All interviews were recorded and transcribed. The research team used a grounded theory approach to analyse the interview data. Results: Both learners and instructors highlighted the benefits of tactile and multi-sensory learning tools, though challenges emerged with the text-based coding platform. Learners self-reported increased confidence, autonomy, and interest in CT skills. Instructors adapted their approaches with detailed verbal descriptions and modifications to tools and lesson plans. Understanding the diverse needs of BVI learners and providing personalized assistance was crucial. Conclusion: Tactile and physical approaches to computational thinking show promise for previously marginalized learners, though challenges remain. Future research will explore how emerging technologies, including AI, can further enhance accessibility for BVI learners.

  PublisherOA PDFDOI

• Development of an Interactive R Shiny Application for Dynamic Health Disparities Research

  CIN Computers Informatics Nursing · 2025-12-10

  articleSenior author

  Although the significance of big data and data science in predicting health outcomes and identifying causal factors is widely recognized, their application in health disparities research remains limited. Understanding health disparities in the visually impaired population requires examining their health behavior patterns and health literacy levels, which can longitudinally impact their health and well-being. In prior research, one of the authors of the study conducted an online survey with 2718 participants using 5 validated self-reported questionnaires, such as Health Promoting Lifestyle Profile II, Health Literacy Questionnaire, eHealth Literacy Questionnaire, General Self-Efficacy, and Center for Epidemiological Studies Depression. Analysis of the online survey data demonstrated that individuals with blindness exhibited significantly higher levels of health-promoting behaviors, health literacy, and eHealth literacy compared to those with moderate and severe low vision. In this study, the research team developed an R Shiny web application as a follow-up to the online survey to disseminate its findings reproducibly and interactively. The R Shiny web application is expected to facilitate reproducible as well as interactive data analysis and sharing more efficiently than traditional methods, such as appendices or Supplementary Materials, Supplemental Digital Content 2, http://links.lww.com/CIN/A463 in academic journals. Extending the research cycle with open datasets and reproducible data analysis can deepen our understanding of health disparities and foster greater collaboration among researchers with similar interests.

  PublisherDOI

• PunchPulse: A Physically Demanding Virtual Reality Boxing Game Designed with, for and by Blind and Low-Vision Players

  2025-10-22 · 2 citations

  preprintOpen accessSenior author

  Blind and low-vision (BLV) individuals experience lower levels of physical activity (PA) compared to sighted peers due to a lack of accessible, engaging exercise options. Existing solutions often rely on auditory cues but do not fully integrate rich sensory feedback or support spatial navigation, limiting their effectiveness. This study introduces PunchPulse, a virtual reality (VR) boxing exergame designed to motivate BLV users to reach and sustain moderate to vigorous physical activity (MVPA) levels. Over a seven-month, multi-phased study, PunchPulse was iteratively refined with three BLV co-designers, informed by two early pilot testers, and evaluated by six additional BLV user-study participants. Data collection included both qualitative (researcher observations, SOPI) and quantitative (MVPA zones, aid usage, completion times) measures of physical exertion and gameplay performance. The user study revealed that all participants reached moderate MVPA thresholds, with high levels of immersion and engagement observed. This work demonstrates the potential of VR as an inclusive medium for promoting meaningful PA in the BLV community and addresses a critical gap in accessible, intensity-driven exercise interventions.

  PublisherDOI

Frequent coauthors

• Byoungju Choi

  12 shared

• Soyoung Choi

  11 shared

• Seunghun Shin

  10 shared

• Mine Dogucu

  Statistical Research (United States)

  6 shared

• Bongshin Lee

  5 shared

• Eun-Hee Goo

  5 shared

• Jaylin Herskovitz

  University of Michigan–Ann Arbor

  4 shared

• Anhong Guo

  Michigan United

  4 shared

Education

• Ph.D., Computer Science

  University of Illinois at Urbana-Champaign

  2008

• M.S., Computer Science

  University of Illinois at Urbana-Champaign

  2003

• B.S., Computer Science

  University of Illinois at Urbana-Champaign

  2001