Atlas of Human-AI Interaction (v1): An Interactive Meta-Science Platform for Large-Scale Research Literature Sensemaking

2025-09-29

AI Summary

Human–AI interaction (HAI) research faces challenges in systematically synthesizing a rapidly growing body of empirical literature and clarifying underlying causal mechanisms. To address this, we introduce the first computational meta-scientific platform tailored for human–computer interaction (HCI), which transcends conventional keyword- or citation-based review paradigms. Our method integrates large language model–driven knowledge extraction, causal identification, knowledge graph construction, and interactive visualization to systematically model design–outcome causal relationships across 2,037 empirical studies. The resulting navigable, reasoning-enabled cognitive graph structurally encodes domain knowledge. Expert evaluation confirms that the graph effectively identifies research gaps and epistemic discontinuities while significantly enhancing cross-study causal inference. This work advances HCI research toward a new paradigm—computational, verifiable, and design-oriented—enabling rigorous, scalable synthesis of empirical evidence.

Technology Category

• Humans and AI: Human-Computer Interaction
• Cognitive Modeling & Cognitive Systems: Simulating Human Behavior
• Search and Optimization: Metareasoning and Metaheuristics

Application Category

• Economics, Online Markets and Human Computation: Research challenges in human and human-AI computation
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Graph Algorithms and Modeling for the Web: Algorithms and analysis for incomplete, noisy, or partially observed Web-related graphs

Abstract

Human-AI interaction researchers face an overwhelming challenge: synthesizing insights from thousands of empirical studies to understand how AI impacts people and inform effective design. Existing approach for literature reviews cluster papers by similarities, keywords or citations, missing the crucial cause-and-effect relationships that reveal how design decisions impact user outcomes. We introduce the Atlas of Human-AI Interaction, an interactive web interface that provides the first systematic mapping of empirical findings across 1,000+ HCI papers using LLM-powered knowledge extraction. Our approach identifies causal relationships, and visualizes them through an AI-enabled interactive web interface as a navigable knowledge graph. We extracted 2,037 empirical findings, revealing research topic clusters, common themes, and disconnected areas. Expert evaluation with 20 researchers revealed the system's effectiveness for discovering research gaps. This work demonstrates how AI can transform literature synthesis itself, offering a scalable framework for evidence-based design, opening new possibilities for computational meta-science across HCI and beyond.

Problem

• Mapping causal relationships in Human-AI interaction literature through knowledge extraction
• Addressing limitations of traditional literature reviews in synthesizing empirical studies
• Developing scalable framework for evidence-based design using computational meta-science

Innovation

• LLM-powered knowledge extraction for causal relationships
• Interactive web interface visualizing navigable knowledge graph
• Scalable framework transforming literature synthesis with AI