Towards Finding Non-obvious Papers: An Analysis of Citation Recommender Systems

TL;DR

This paper analyzes citation recommendation systems, revealing their limitations in finding loosely connected papers, and proposes combining multiple data sources and algorithms to improve recommendation diversity and efficiency.

Contribution

It introduces a novel analysis of citation graph properties and proposes combining author, venue, and keyword data to enhance citation recommendation methods.

Findings

Existing methods mainly find highly connected papers

Loosely connected papers are underrepresented in recommendations

Combining multiple data sources improves recommendation diversity

Abstract

As science advances, the academic community has published millions of research papers. Researchers devote time and effort to search relevant manuscripts when writing a paper or simply to keep up with current research. In this paper, we consider the problem of citation recommendation by extending a set of known-to-be-relevant references. Our analysis shows the degrees of cited papers in the subgraph induced by the citations of a paper, called projection graph, follow a power law distribution. Existing popular methods are only good at finding the long tail papers, the ones that are highly connected to others. In other words, the majority of cited papers are loosely connected in the projection graph but they are not going to be found by existing methods. To address this problem, we propose to combine author, venue and keyword information to interpret the citation behavior behind those loosely connected papers. Results show that different methods are finding cited papers with widely different properties. We suggest multiple recommended lists by different algorithms could satisfy various users for a real citation recommendation system. Moreover, we also explore the fast local approximation for combined methods in order to improve the efficiency.