Personalized Entity Search by Sparse and Scrutable User Profiles

TL;DR

This paper explores personalized entity search, specifically for books, using sparse user profiles from questionnaires, and demonstrates that even minimal personal data can improve search relevance.

Contribution

It introduces a novel approach to personalize entity search by leveraging sparse user profiles, which has been underexplored compared to query logs and purchase histories.

Findings

Sparse user profiles improve search effectiveness.

Language model and neural re-ranking methods are effective.

Personalization benefits are evident even with minimal user data.

Abstract

Prior work on personalizing web search results has focused on considering query-and-click logs to capture users individual interests. For product search, extensive user histories about purchases and ratings have been exploited. However, for general entity search, such as for books on specific topics or travel destinations with certain features, personalization is largely underexplored. In this paper, we address personalization of book search, as an exemplary case of entity search, by exploiting sparse user profiles obtained through online questionnaires. We devise and compare a variety of re-ranking methods based on language models or neural learning. Our experiments show that even very sparse information about individuals can enhance the effectiveness of the search results.