Learning to Rank for Expert Search in Digital Libraries of Academic Publications

TL;DR

This paper introduces a learning to rank approach for expert search in digital academic libraries, effectively combining textual, graph-structure, citation, and profile data to improve expert identification.

Contribution

It presents a novel principled method using learning to rank to integrate multiple evidence sources for expert finding in academic digital libraries.

Findings

Learning to rank improves expert search accuracy.

Combining multiple evidence sources enhances expert identification.

Proposed methods are effective on a Computer Science publication dataset.

Abstract

The task of expert finding has been getting increasing attention in information retrieval literature. However, the current state-of-the-art is still lacking in principled approaches for combining different sources of evidence in an optimal way. This paper explores the usage of learning to rank methods as a principled approach for combining multiple estimators of expertise, derived from the textual contents, from the graph-structure with the citation patterns for the community of experts, and from profile information about the experts. Experiments made over a dataset of academic publications, for the area of Computer Science, attest for the adequacy of the proposed approaches.