A Bias-Free Time-Aware PageRank Algorithm for Paper Ranking in Dynamic Citation Networks

Abstract
The process of ranking scientific publications in dynamic citation networks plays a crucial rule in a variety of applications. Despite the availability of a number of ranking algorithms, most of them use common popularity metrics such as the citation count, h-index, and Impact Factor (IF). These adopted metrics cause a problem of bias in favor of older publications that took enough time to collect as many citations as possible. This paper focuses on solving the problem of bias by proposing a new ranking algorithm based on the PageRank (PR) algorithm; it is one of the main page ranking algorithms being widely used. The developed algorithm considers a newly suggested metric called the Citation Average rate of Change (CAC). Time information such as publication date and the citation occurrence’s time are used along with citation data to calculate the new metric. The proposed ranking algorithm was tested on a dataset of scientific papers in the field of medical physics published in the Dimensions database from years 2005 to 2017. The experimental results have shown that the proposed ranking algorithm outperforms the PageRank algorithm in ranking scientific publications where 26 papers instead of only 14 were ranked among the top 100 papers of this dataset. In addition, there were no radical changes or unreasonable jump in the ranking process, i.e., the correlation rate between the results of the proposed ranking method and the original PageRank algorithm was 92% based on the Spearman correlation coefficient.

This publication has 27 references indexed in Scilit: