Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Rules, Resources, and Restrictions: A Taxonomy of Task-Based Information Request Intents

Melanie A. Kilian, David Elsweiler

TL;DR

This paper introduces a task-based information request intents taxonomy derived from grounded-theory interviews with eight airport information clerks, addressing the gap between query-centric taxonomies and AI-driven task support. It presents a 4-layer taxonomy with 20 level-1 categories and 86 sub-categories that connect user goals to underlying tasks, emphasizing rules for action, resources, practices, and progression cues. The study demonstrates that task context modulates expected answer types, with planning tasks typically requiring less detail than execution tasks, and maps the taxonomy to existing intent frameworks to highlight its integrative value. The practical contribution lies in informing AI-driven conversational search systems to provide contextual, task-oriented assistance while acknowledging limitations related to venue-specific data and retrospective reporting.

Abstract

Understanding and classifying query intents can improve retrieval effectiveness by helping align search results with the motivations behind user queries. However, existing intent taxonomies are typically derived from system log data and capture mostly isolated information needs, while the broader task context often remains unaddressed. This limitation becomes increasingly relevant as interactions with Large Language Models (LLMs) expand user expectations from simple query answering toward comprehensive task support, for example, with purchasing decisions or in travel planning. At the same time, current LLMs still struggle to fully interpret complex and multifaceted tasks. To address this gap, we argue for a stronger task-based perspective on query intent. Drawing on a grounded-theory-based interview study with airport information clerks, we present a taxonomy of task-based information request intents that bridges the gap between traditional query-focused approaches and the emerging demands of AI-driven task-oriented search.

Rules, Resources, and Restrictions: A Taxonomy of Task-Based Information Request Intents

TL;DR

This paper introduces a task-based information request intents taxonomy derived from grounded-theory interviews with eight airport information clerks, addressing the gap between query-centric taxonomies and AI-driven task support. It presents a 4-layer taxonomy with 20 level-1 categories and 86 sub-categories that connect user goals to underlying tasks, emphasizing rules for action, resources, practices, and progression cues. The study demonstrates that task context modulates expected answer types, with planning tasks typically requiring less detail than execution tasks, and maps the taxonomy to existing intent frameworks to highlight its integrative value. The practical contribution lies in informing AI-driven conversational search systems to provide contextual, task-oriented assistance while acknowledging limitations related to venue-specific data and retrospective reporting.

Abstract

Understanding and classifying query intents can improve retrieval effectiveness by helping align search results with the motivations behind user queries. However, existing intent taxonomies are typically derived from system log data and capture mostly isolated information needs, while the broader task context often remains unaddressed. This limitation becomes increasingly relevant as interactions with Large Language Models (LLMs) expand user expectations from simple query answering toward comprehensive task support, for example, with purchasing decisions or in travel planning. At the same time, current LLMs still struggle to fully interpret complex and multifaceted tasks. To address this gap, we argue for a stronger task-based perspective on query intent. Drawing on a grounded-theory-based interview study with airport information clerks, we present a taxonomy of task-based information request intents that bridges the gap between traditional query-focused approaches and the emerging demands of AI-driven task-oriented search.
Paper Structure (27 sections, 1 figure, 7 tables)

This paper contains 27 sections, 1 figure, 7 tables.

Table of Contents

  1. Introduction
  2. Related Work
  3. Research on Query Intent Classification
  4. Research on Task-Based IR
  5. Methodology
  6. General Methodological Approach
  7. Participants
  8. Methods for Data Collection
  9. Taxonomy Building: Methods for Data Analysis
  10. Taxonomy Evaluation
  11. Findings: A Taxonomy of Task-Based Information Request Intents
  12. Taxonomy Overview and Distinct Features
  13. Rules for Action: Necessities and Permissibilities
  14. Resources and Possibilities for Action
  15. Specific Practices for Action
  16. ...and 12 more sections

Figures (1)

  • Figure 1: The top levels of the task-based request intent taxonomy