Will This Paper Increase Your h-index?

A widely used measure of scientific impact is citations. However, due to their power-law distribution, citations are fundamentally difficult to predict. Instead, to characterize scientific impact, we address two analogous questions asked by many scientifi

  • PDF / 837,451 Bytes
  • 5 Pages / 439.37 x 666.142 pts Page_size
  • 91 Downloads / 164 Views

DOWNLOAD

REPORT


Abstract. A widely used measure of scientific impact is citations. However, due to their power-law distribution, citations are fundamentally difficult to predict. Instead, to characterize scientific impact, we address two analogous questions asked by many scientific researchers: “How will my h-index evolve over time, and which of my previously or newly published papers will contribute to it?” To answer these questions, we perform two related tasks. First, we develop a model to predict authors’ future h-indices based on their current scientific impact. Second, we examine the factors that drive papers—either previously or newly published—to increase their authors’ predicted future h-indices. By leveraging relevant factors, we can predict an author’s h-index in five years with an R2 value of 0.92 and whether a previously (newly) published paper will contribute to this future h-index with an F1 score of 0.99 (0.77). We find that topical authority and publication venue are crucial to these effective predictions, while topic popularity is surprisingly inconsequential. Further, we develop an online tool that allows users to generate informed h-index predictions. Our work demonstrates the predictability of scientific impact, and can help researchers to effectively leverage their scholarly position of “standing on the shoulders of giants.”

Scientific impact plays a pivotal role in the evaluation of the output of scholars, departments, and institutions. A widely used measure of scientific impact is citations, with a growing body of literature focused on predicting the number of citations obtained by any given publication. The effectiveness of citation prediction, however, is fundamentally limited by their power-law distribution, whereby publications with few citations are extremely common and publications with many citations are relatively rare. In light of this limitation, we instead investigate scientific impact by addressing two analogous questions [1], both related to the measure of h-index [2] and asked by many academic researchers: “How will my h-index evolve over time, and which of my previously and newly published papers will contribute to my future h-index? ” Y. Dong and R.A. Johnson—Provided equal contribution to this work. This work was published at the 8th ACM International Conference on Web Search and Data Mining (WSDM’15 ) [1]. This extended abstract has been largely extracted from the publication. c Springer International Publishing Switzerland 2015  A. Bifet et al. (Eds.): ECML PKDD 2015, Part III, LNAI 9286, pp. 259–263, 2015. DOI: 10.1007/978-3-319-23461-8 26

260

Y. Dong et al.

t h-index: h

m

t+ t h-index: ?

n

Fig. 1. Illustrative example of scientific impact prediction. Before time t, a scholar published m papers and had an h-index of h. Our prediction problems are targeted at answering two questions: 1) First, what is the scholar’s future h-index, h , at time t+Δt? 2) Second, which of his/her papers, both (a) those m papers previously published before t and (b) those n new papers published at t, will contrib