Ranking Scientific Articles in a Dynamically Evolving Citation Network

Abstract

Scientific ranking has long been a hot and important topic in both computer science and scientometrics. A lot of statistics-based and graph-based methods have been proposed for calculating a prestige value as the assessment of each paper's scientific influence. However, being ignorant of the dynamic nature of scientific publication and science evolution, all these methods present a biased point of view of scientific influence. Besides, the ranking results of these methods are not accessible to users because of lack of an explainable model. As an alternative to the state-of-the-art, this paper proposes a cognitively explainable model by integrating three factors in scientific development including knowledge accumulation by individual papers, knowledge diffusion through citation behaviour and knowledge decay with time elapse. Evaluated on ACL Anthology Network using the reference lists of four textbooks or handbooks as the gold standard, the proposed model is proved to be effective in scientific ranking and potential for new insights into the definition and measurement of scientific influence.

Cite this work

No public copy is stored for this record, so only the metadata is cited.

Stored only when both papers are in the corpus — 6 citations exist upstream.