A Term-Based Methodology for Query Reformulation Understanding

TL;DR

This paper introduces a new term-based methodology to analyze and interpret user query reformulations in session search, leveraging query logs and click data to understand user behavior and motivations.

Contribution

The paper presents a novel term-based approach for understanding query reformulations, demonstrating its effectiveness using TREC Session Track data and click data analysis.

Findings

The methodology accurately identifies query reformulation strategies.

It provides insights into user motivations during session search.

The approach improves understanding of query evolution and user interaction.

Abstract

Key to any research involving session search is the understanding of how a user's queries evolve throughout the session. When a user creates a query reformulation, he or she is consciously retaining terms from their original query, removing others and adding new terms. By measuring the similarity between queries we can make inferences on the user's information need and how successful their new query is likely to be. By identifying the origins of added terms we can infer the user's motivations and gain an understanding of their interactions. In this paper we present a novel term-based methodology for understanding and interpreting query reformulation actions. We use TREC Session Track data to demonstrate how our technique is able to learn from query logs and we make use of click data to test user interaction behavior when reformulating queries. We identify and evaluate a range of term-based query reformulation strategies and show that our methods provide valuable insight into understanding query reformulation in session search.