Taxonomy of User Needs and Actions

2025-10-07

AI Summary

Existing dialogue act taxonomies suffer from coarse granularity, domain specificity, or functional narrowness, failing to simultaneously accommodate users’ instrumental goals and context-sensitive, adaptive, and socially embedded practices. To address this, we conducted iterative qualitative analysis of 1,193 real-world human-AI dialogues, yielding TUNA—a three-level, empirically grounded taxonomy of user needs and behaviors spanning information seeking, content generation, and social interaction. TUNA is the first multi-scale user behavior model integrating contextual awareness, adaptivity, and sociality, transcending the functional monism of traditional dialogue frameworks. It enables cross-domain strategy coordination and hierarchical extensibility while providing an evidence-driven descriptive language for AI usage—enhancing dialogue system interpretability, safety, and accountability. Validated across diverse applications, TUNA bridges academic research and industrial practice.

Technology Category

• Humans and AI: Human-Aware Planning and Behavior Prediction
• Natural Language Processing: Conversational AI/Dialog Systems
• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• User Modeling, Personalization and Recommendation: User modeling and simulation for interactive and conversational systems
• Search and Retrieval-Augmented AI: Assisted, interactive, and conversational search

Abstract

The growing ubiquity of conversational AI highlights the need for frameworks that capture not only users' instrumental goals but also the situated, adaptive, and social practices through which they achieve them. Existing taxonomies of conversational behavior either overgeneralize, remain domain-specific, or reduce interactions to narrow dialogue functions. To address this gap, we introduce the Taxonomy of User Needs and Actions (TUNA), an empirically grounded framework developed through iterative qualitative analysis of 1193 human-AI conversations, supplemented by theoretical review and validation across diverse contexts. TUNA organizes user actions into a three-level hierarchy encompassing behaviors associated with information seeking, synthesis, procedural guidance, content creation, social interaction, and meta-conversation. By centering user agency and appropriation practices, TUNA enables multi-scale evaluation, supports policy harmonization across products, and provides a backbone for layering domain-specific taxonomies. This work contributes a systematic vocabulary for describing AI use, advancing both scholarly understanding and practical design of safer, more responsive, and more accountable conversational systems.

Problem

• Addresses the lack of comprehensive frameworks for user conversational behavior
• Develops a taxonomy to classify diverse user-AI interaction types and goals
• Provides systematic vocabulary for evaluating and designing responsive conversational systems

Innovation

• TUNA framework organizes user actions hierarchically
• Developed through qualitative analysis of human-AI conversations
• Enables multi-scale evaluation and policy harmonization across products