Expertise modeling for matching papers with reviewers

TLDR

Expertise modeling is essential for matching reviewers to submitted papers. The study evaluates measures of author–document association to improve reviewer matching. The authors compare two language‑model approaches with a novel Author‑Persona‑Topic model that represents each author with multiple persona‑topic distributions, using papers from the Rexa database and a reviewer‑matching task with human relevance judgments. The APT model outperforms the other approaches.

Abstract

An essential part of an expert-finding task, such as matching reviewers to submitted papers, is the ability to model the expertise of a person based on documents. We evaluate several measures of the association between an author in an existing collection of research papers and a previously unseen document. We compare two language model based approaches with a novel topic model, Author-Persona-Topic (APT). In this model, each author can write under one or more "personas," which are represented as independent distributions over hidden topics. Examples of previous papers written by prospective reviewers are gathered from the Rexa database, which extracts and disambiguates author mentions from documents gathered from the web. We evaluate the models using a reviewer matching task based on human relevance judgments determining how well the expertise of proposed reviewers matches a submission. We find that the APT topic model outperforms the other models.