Science and Technology for
Augmenting Reading
Definition
Interfaces that in some way alter the text we read. A simple example of this is adding some additional text on an unfamiliar term like “augmented reading”, but it could also include changing the structure or fonts of a text, drawing in new information, or interactively expanding and contracting text.
(STAR)
What does the future hold for how we read?
Submission Details
Call for Papers
We are always reading, whether it is a research paper, news article, text message, chatbot response, or website. Better reading technology could transform texts so that they are easier to read, surface hard-to-find information or support synthesis.
Recent changes in the technological landscape are significantly changing the reading experience. AI has introduced many new possibilities for interfaces to augment or transform text to be more rapidly scanned, navigated, understood, and compared to other texts. What does this future hold for reading?
Join us to work to answer that question at the first CHI workshop on the Science & Technology of Augmented Reading (STAR). Come together with researchers from HCI and AI to work through ideas in augmented reading, including but not limited to:
- Novel interaction and visual designs for texts
- Multi-modal, dynamic, and malleable reading experiences
- Accessible and adaptive texts
- The application of AI (agents, LLMs, VLMs, etc.) to text generation and augmentation
- Guidance and open questions in evaluation methods (e.g., observation techniques, comprehension assessments, remote and at scale evaluation methods)
- Reviews of theories of reading behavior and cognition
- Development of new theories of augmented reading
- Critiques of the notion of augmented reading
- Experience reports of deployed augmented reading interfaces
- Instantiations of augmented reading in domains you personally care about, such as education, news, law, programming, and research
At the workshop itself, you will see and be a part of round-the-room 1-minute lightning talks, followed by speculative design and research activities in small interest groups formed at the event. We can't wait to see you there!
Example papers
The following are papers that have appeared at CHI, UIST, and other venues covering many of the themes from this workshop. Of course, the papers you submit to this workshop will be shorter and can cover ideas that are developing rather than completely finished.
- Constrained Highlighting in a Document Reader can Improve Reading Comprehension
- Augmented Physics: Creating Interactive and Embedded Physics Simulations from Static Textbook Diagrams
- Increasing the Transparency of Research Papers with Explorable Multiverse Analyses
- Capture & Analysis of Active Reading Behaviors for Interactive Articles on the Web
- CriTrainer: An Adaptive Training Tool for Critical Paper Reading
- Successful classroom deployment of a social document annotation system
- MindDot: Supporting Effective Cognitive Behaviors in Concept Map-Based Learning Environments
- MedKnowts: Unified Documentation and Information Retrieval for Electronic Health Records
- Log-it: Supporting Programming with Interactive, Contextual, Structured, and Visual Logs
- H❤️rtDown: Document Processor for Executable Linear Algebra Papers
- Reading on Smart Glasses: The Effect of Text Position, Presentation Type and Walking
Timeline
Program
Welcome & Opening Remarks
Overview of workshop goals.
Introductions (Lightning Talks)
Each participant presents a single slide on "what they are thinking about right now" (1 min/person).
Affinity Group Activities
Small groups focusing on: Novel Interfaces, Emerging Problems, or Evaluation Techniques.
Organizers
Tal August
University of Illinois Urbana Champaign
ContactExpertise:
Assistant professor at UIUC. Improves communication of knowledge-intensive text by adapting language to audiences. Develops reading and writing innovations for medical, legal, scientific, and instructional texts.
Andrew Head
University of Pennsylvania
Expertise:
Develops novel interactions for reading and reasoning. Lowers barriers to understanding complex technical content. Led work on AI2's Semantic Reader and developed interfaces for augmented reading of scholarly texts, math, code, and medical documents.
Alexa Siu
Adobe Research
Expertise:
Research scientist focused on human-AI interactions that improve productivity and accessibility. Recent work on sensemaking over document collections, document Q&A, and editing. Contributed to Acrobat AI Assistant.
Elena L. Glassman
Harvard University
Expertise:
Builds AI-resilient interfaces that augment skimming, writing, and close reading of code and text. Specializes in leveraging theories of human cognition to help users form mental models from concrete examples.
Jonathan Kummerfeld
University of Sydney
Expertise:
Focuses on interactions between people and NLP systems. Develops more effective algorithms, workflows, and systems for collaboration including rapid text reading and methods for highlighting differences across language model outputs.
Joseph Chee Chang
Allen Institute for AI
Expertise:
Senior researcher focused on human-AI systems for sensemaking and managing information overload. Recent work centers on literature review support tools for searching, discovering, and synthesizing research papers.
Lucy Lu Wang
University of Washington
Expertise:
Improves accessibility of scientific text for high-expertise domains like healthcare. Co-organizer of SciNLP and Scholarly Document Processing workshops. Visiting scientist at the Allen Institute for AI.
Marti A. Hearst
UC Berkeley
Expertise:
Professor with research in user interfaces for search, information visualization for text, and computational linguistics. ACM Fellow and ALF. Former ACL President. Led the Semantic Reader project on augmented reading interfaces.