Urbanite: A Dataflow-Based Framework for Human-AI Interactive Alignment in Urban Visual Analytics

2025-08-10

AI Summary

Human-AI collaboration in urban visual analytics remains challenging due to the difficulty of integrating domain expertise with AI systems, particularly for non-technical users lacking proficiency in complex analytical workflows. Method: This paper proposes a dataflow-based interactive alignment framework featuring a novel multi-resolution intent modeling mechanism, enabling users to articulate and dynamically refine analytical intent across granular levels—including task definition, node configuration, and parameter tuning. The framework integrates large language model (LLM) interfaces, visual programming, and provenance tracking to ensure end-to-end interpretability and traceability among user intent, system behavior, and analytical outputs. Contribution/Results: Evaluated across multiple urban-domain applications, the framework significantly lowers the barrier to building analytical systems, enhances human-AI collaboration efficiency, and improves process transparency through rigorous intent-behavior-result alignment.

Technology Category

• Humans and AI: Intelligent User Interfaces
• Application Domains: Humanities & Computational Social Science
• Computer Vision: Visual Reasoning & Symbolic Representations

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Web Mining and Content Analysis: Web data visualization
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

Abstract

With the growing availability of urban data and the increasing complexity of societal challenges, visual analytics has become essential for deriving insights into pressing real-world problems. However, analyzing such data is inherently complex and iterative, requiring expertise across multiple domains. The need to manage diverse datasets, distill intricate workflows, and integrate various analytical methods presents a high barrier to entry, especially for researchers and urban experts who lack proficiency in data management, machine learning, and visualization. Advancements in large language models offer a promising solution to lower the barriers to the construction of analytics systems by enabling users to specify intent rather than define precise computational operations. However, this shift from explicit operations to intent-based interaction introduces challenges in ensuring alignment throughout the design and development process. Without proper mechanisms, gaps can emerge between user intent, system behavior, and analytical outcomes. To address these challenges, we propose Urbanite, a framework for human-AI collaboration in urban visual analytics. Urbanite leverages a dataflow-based model that allows users to specify intent at multiple scopes, enabling interactive alignment across the specification, process, and evaluation stages of urban analytics. Based on findings from a survey to uncover challenges, Urbanite incorporates features to facilitate explainability, multi-resolution definition of tasks across dataflows, nodes, and parameters, while supporting the provenance of interactions. We demonstrate Urbanite's effectiveness through usage scenarios created in collaboration with urban experts. Urbanite is available at https://urbantk.org/urbanite.

Problem

• Reducing complexity in urban data analysis for non-experts
• Bridging gaps between user intent and system outcomes
• Enabling interactive alignment in visual analytics workflows

Innovation

• Dataflow-based model for intent specification
• Interactive alignment across multiple stages
• Multi-resolution task definition in dataflows