h-Index-based link prediction methods in citation network

Link prediction implies the mining of the missing links in networks or prediction of the next node pair to be connected by a link. Link prediction is useful for mining information in citation networks, and most of the existing related studies commonly use degree rather than more advanced methods to measure the importance of nodes. However, such a method cannot easily measure the importance of a paper in reality; some papers have high degree in citation networks but are not very influential. This issue restricts the performance of the link prediction methods applied to citation networks. The current study analyzed h-type indices, which are more suitable than degree for measuring the importance of citation network nodes. We propose two h-index-based link prediction methods. Experiments conducted on real citation networks demonstrate that the use of h-type index to measure the importance of nodes in citation networks can significantly improve the prediction accuracy of link prediction methods.

[1]  András Schubert,et al.  Hirsch-type indices for characterizing networks , 2009, Scientometrics.

[2]  Muhammad Arshad Islam,et al.  Predicting scientific impact based on h-index , 2018, Scientometrics.

[3]  Benjamin F. Jones,et al.  Atypical Combinations and Scientific Impact , 2013, Science.

[4]  Yang Yang,et al.  Small vulnerable sets determine large network cascades in power grids , 2017, Science.

[5]  Dima Shepelyansky,et al.  Google matrix analysis of directed networks , 2014, ArXiv.

[6]  Michael McGill,et al.  Introduction to Modern Information Retrieval , 1983 .

[7]  Lise Getoor,et al.  Link mining: a survey , 2005, SKDD.

[8]  M. Newman,et al.  Hierarchical structure and the prediction of missing links in networks , 2008, Nature.

[9]  Lev Muchnik,et al.  Identifying influential spreaders in complex networks , 2010, 1001.5285.

[10]  Roger Guimerà,et al.  Missing and spurious interactions and the reconstruction of complex networks , 2009, Proceedings of the National Academy of Sciences.

[11]  Linyuan Lu,et al.  Link Prediction in Complex Networks: A Survey , 2010, ArXiv.

[12]  András Schubert,et al.  Using the h-index for assessing single publications , 2009, Scientometrics.

[13]  A. Telcs,et al.  Lobby index in networks , 2008, 0809.0514.

[14]  D J PRICE,et al.  NETWORKS OF SCIENTIFIC PAPERS. , 1965, Science.

[15]  Tao Zhou,et al.  The H-index of a network node and its relation to degree and coreness , 2016, Nature Communications.

[16]  Osame Kinouchi,et al.  Lobby index as a network centrality measure , 2013 .

[17]  J. E. Hirsch,et al.  An index to quantify an individual's scientific research output , 2005, Proc. Natl. Acad. Sci. USA.

[18]  David F. Gleich,et al.  PageRank beyond the Web , 2014, SIAM Rev..

[19]  Lada A. Adamic,et al.  Friends and neighbors on the Web , 2003, Soc. Networks.

[20]  Wolfgang Glänzel.  The role of core documents in bibliometric network analysis and their relation with h-type indices , 2012, Scientometrics.

[21]  Mark Newman,et al.  Networks: An Introduction , 2010 .