Abstract：Existing methods have problems such as low accuracy or time consuming. Through empirical analysis of real data sets, we find that there is a strong correlation between future citations and annual citation of papers, i.e. the sustained attention; meanwhile, the future citations have apparent characteristics of time decay. Thus we put forward a method based on sustained attention decay to predict the future citations of papers, and then to find papers of potential importance with these results. Experimental results on two benchmark data sets show that the proposed method can predict precisely with lower time complexity.
[1] Wang D, Song C, Barabási A L. Quantifying long-term scientific impact[J]. Science, 2013, 342(6154): 127-132. [2] Hirsch J E. An index to quantify an individual's scientific research output[J]. Proceedings of the National academy of Sciences of the United States of America, 2005, 102(46): 16569-16572. [3] Egghe L. Theory and practise of the g-index[J]. Scientometrics, 2006, 69(1): 131-152. [4] Ding Y, Yan E, Frazho A, et al. PageRank for ranking authors in co-citation networks[J]. Journal of the American Society for Information Science and Technology, 2009, 60(11): 2229-2243. [5] Liu X, Bollen J, Nelson M L, et al. Co-authorship networks in the digital library research community[J]. Information Processing & Management, 2005, 41(6): 1462-1480. [6] Medo M, Cimini G, Gualdi S. Temporal effects in the growth of networks[J]. Physical Review Letters, 2011, 107(23): 238701. [7] Berberich K, Vazirgiannis M, Weikum G. Time-aware authority ranking[J]. Internet Mathematics, 2005, 2(3): 301-332. [8] Walker D, Xie H, Yan K K, et al. Ranking scientific publications using a model of network traffic[J]. Journal of Statistical Mechanics: Theory and Experiment, 2007, 2007(06): P06010. [9] Zhou Y B, Lü L, Li M. Quantifying the influence of scientists and their publications: distinguishing between prestige and popularity[J]. New Journal of Physics, 2012, 14(3): 033033. [10] Yan E, Ding Y, Sugimoto C R. P-Rank: an indicator measuring prestige in heterogeneous scholarly networks[J]. Journal of the American Society for Information Science and Technology, 2011, 62(3): 467-477. [11] Zhou D, Orshanskiy S A, Zha H, et al. Co-ranking authors and documents in a heterogeneous network[J]. IEEE International Conference on Data Mining, 2007, 739-744. [12] Kleinberg J M. Authoritative sources in a hyperlinked environment[J]. Journal of the ACM (JACM), 1999, 46(5): 604-632. [13] Shen H, Wang D, Song C, et al. Modeling and predicting popularity dynamics via reinforced poisson processes[J]. Eprint arXiv, 2014: arXiv:1401.0778. [14] Yan E, Ding Y. Weighted citation: an indicator of an article's prestige[J]. Journal of the American Society for Information Science and Techno-logy, 2010, 61(8): 1635-1643. [15] Sayyadi H, Getoor L. FutureRank: ranking scientific articles by predicting their future pagerank[J]. Proc of Siam International Conference on Data Mining, 2009: 533-544. [16] Page L, Brin S, Motwani R, et al. The pageRank citation ranking: bringing order to the web[J]. Lecture Notes in Engineering, 1998,9(1): 1-14. [17] Radicchi F, Fortunato S, Vespignani A. Citation networks[J]. Understanding Complex Systems, 2012: 233-257. [18] Wu Z X, Holme P. Modeling scientific-citation patterns and other triangle-rich acyclic networks[J]. Physicl Review E, 2009, 80(3): 037101. [19] Newman M E J. Prediction of highly cited papers[J]. Earophysics Letters, 2014,105(2): 28002-28007. [20] Newman M E J. The first-mover advantage in scientific publication[J]. Europhysics Letters, 2009, 86(6): 68001.
