Welcome to the

Data SemanticsLab

We investigate how meaning is represented, communicated, and negotiated between people, data, and intelligent systems.

Research Themes

Language, Intent, and Interaction

How do people express what they mean and what they want to know?

Representative work for Language, Intent, and Interaction

People communicate goals and questions through language, context, reference, ambiguity, and interaction. We study how computational systems can understand human intent, interpret incomplete or domain-specific expressions, and support meaning as it develops through conversation.

Selected Papers

Lexara: A User-Centered Toolkit for Evaluating Large Language Models for Conversational Visual AnalyticsSrishti Palani, Vidya SetlurACM CHI Conference on Human Factors in Computing Systems2026
From Delays to Densities: Exploring Data Uncertainty through Speech, Text, and VisualizationChase Stokes, Chelsea Sanker, Bridget Cogley, Vidya SetlurEuroVis2024
Comparison Conundrum and the Chamber of Visualizations: An Exploration of How Language Influences Visual DesignAimen Gaba, Vidya Setlur, Arjun Srinivasan, Jane Hoffswell
Cindy Xiong BearfieldIEEE Transactions on Visualization and Computer Graphics2022

Visual Representation and Sensemaking

How do representations shape what people understand?

Representative work for Visual Representation and Sensemaking

Visual representations shape what people notice, compare, interpret, and infer from data. We investigate how people create, navigate, and critique visualizations, and how representations can better support exploration, reasoning, and sensemaking.

Selected Papers

Not Always Top-Left: Untangling the Signals that Guide Dashboard Reading OrderNicole Sultanum, Vidya SetlurIEEE Transactions on Visualization and Computer Graphics2026
EmphasisChecker: A Tool for Guiding Chart and Caption EmphasisDae Hyun Kim, Seulgi Choi, Juho Kim, Vidya Setlur, Maneesh AgrawalaIEEE Transactions on Visualization and Computer Graphics2023
Striking a Balance: Reader Takeaways and Preferences when Integrating Text and ChartsChase Stokes, Vidya Setlur, Bridget Cogley, Arvind Satyanarayan, Marti HearstEuroVis2024

Intelligent Systems and Human-AI Collaboration

How can people and intelligent systems reason together?

Representative work for Intelligent Systems and Human-AI Collaboration

AI systems increasingly participate in analysis by generating interpretations, recommendations, visualizations, and workflows. We study how these systems reason with context and analytical state, and how people can understand, steer, verify, and collaborate with them while retaining meaningful control.

Selected Papers

Jupybara: Operationalizing a Design Space for Actionable Data Analysis and Storytelling with LLMsHuichen Will Wang, Larry Birnbaum, Vidya SetlurACM CHI Conference on Human Factors in Computing Systems2025
AI-Enabled Conversational Journaling for Advancing Parkinson's Disease Symptom TrackingMashrur Rashik, Shilpa Sweth, Nishtha Agrawal, Saiyyam Kochar, Kara M. Smith, Fateme Rajabiyazdi, Vidya Setlur, Narges Mahyar, Ali SarvghadACM CHI Conference on Human Factors in Computing Systems2025 · Best Paper Honorable Mention
Olio: A Semantic Search Interface for Data RepositoriesVidya Setlur, Andriy Kanyuka, Arjun SrinivasanACM Symposium on User Interface Software and Technology2023