An Extended Relevance Model for Session Search

TL;DR

This paper introduces an extended relevance model for session search that dynamically captures user information needs based on query reformulations and behavioral influence, significantly improving search effectiveness.

Contribution

The paper presents a novel relevance model that incorporates user query reformulation dynamics and behavioral influence to enhance session search performance.

Findings

Significant boost in session search performance

Effective modeling of user query reformulation

Improved relevance estimation based on user behavior

Abstract

The session search task aims at best serving the user's information need given her previous search behavior during the session. We propose an extended relevance model that captures the user's dynamic information need in the session. Our relevance modelling approach is directly driven by the user's query reformulation (change) decisions and the estimate of how much the user's search behavior affects such decisions. Overall, we demonstrate that, the proposed approach significantly boosts session search performance.