Predicting the popularity of scientific publications by an age-based diffusion model

TL;DR

This paper introduces an age-based diffusion model to predict future citation counts and popularity of scientific papers, outperforming existing network-based methods especially for newly published, less-cited papers.

Contribution

The paper proposes a novel age-based diffusion model that improves prediction accuracy of paper popularity and citation counts, particularly for recent publications.

Findings

AD model outperforms other network-based methods in prediction accuracy

The model significantly improves rankings of newly published papers

It helps identify future highly cited papers early

Abstract

Predicting the popularity of scientific publications has attracted many attentions from various disciplines. In this paper, we focus on the popularity prediction problem of scientific papers, and propose an age-based diffusion (AD) model to identify which paper will receive more citations in the near future and will be popular. The AD model is a mimic of the attention diffusion process along the citation networks. The experimental study shows that the AD model can achieve better prediction accuracy than other networkbased methods. For some newly published papers that have not accumulated many citations but will be popular in the near future, the AD model can substantially improve their rankings. This is really critical, because identifying the future highly cited papers from massive numbers of new papers published each month would provide very valuable references for researchers.