All Fingers are not Equal: Intensity of References in Scientific Articles

TL;DR

This paper introduces a new approach to measure the importance of citations in scientific articles by analyzing reference intensity, leading to improved understanding and applications in citation analysis.

Contribution

It presents a novel graph-based semi-supervised model, GraLap, for labeling reference intensity and demonstrates its effectiveness on real datasets.

Findings

46% better correlation with true reference labels

Significant improvement over baseline methods

Four applications showcasing practical benefits

Abstract

Research accomplishment is usually measured by considering all citations with equal importance, thus ignoring the wide variety of purposes an article is being cited for. Here, we posit that measuring the intensity of a reference is crucial not only to perceive better understanding of research endeavor, but also to improve the quality of citation-based applications. To this end, we collect a rich annotated dataset with references labeled by the intensity, and propose a novel graph-based semi-supervised model, GraLap to label the intensity of references. Experiments with AAN datasets show a significant improvement compared to the baselines to achieve the true labels of the references (46% better correlation). Finally, we provide four applications to demonstrate how the knowledge of reference intensity leads to design better real-world applications.