PageRank-based talent mining algorithm based on Web of Science

doi:10.11772/j.issn.1001-9081.2020081206

Journal of Computer Applications ›› 2021, Vol. 41 ›› Issue (5): 1356-1360.DOI: 10.11772/j.issn.1001-9081.2020081206

Special Issue: 数据科学与技术

• Data science and technology • Previous Articles Next Articles

PageRank-based talent mining algorithm based on Web of Science

LI Chong¹, WANG Yuchen^1,2, DU Weijing^1,2, HE Xiaotao¹, LIU Xuemin¹, ZHANG Shibo¹, LI Shuren¹

1. Computer Network Information Center, Chinese Academy of Sciences, Beijing 100190, China;
2. University of Chinese Academy of Sciences, Beijing 100049, China

Received:2020-08-10 Revised:2020-10-30 Online:2021-05-10 Published:2021-05-19
Supported by:
This work is partially supported by the CAS Informatization Special Project in the 13th Five-Year Plan (XXH13504-03).

基于Web of Science的PageRank人才挖掘算法

李翀¹, 王宇宸^1,2, 杜伟静^1,2, 何晓涛¹, 刘学敏¹, 张士波¹, 李树仁¹

1. 中国科学院计算机网络信息中心, 北京 100190;
2. 中国科学院大学, 北京 100049

通讯作者: 王宇宸
作者简介:李翀(1978-),男,安徽霍邱人,高级工程师,博士,CCF高级会员,主要研究方向:大数据、推荐系统;王宇宸(1996-),男,安徽怀远人,硕士研究生,主要研究方向:大数据管理;杜伟静(1993-),女,河北廊坊人,硕士研究生,主要研究方向:大数据管理;何晓涛(1971-),女,河北衡水人,高级工程师,硕士,主要研究方向:数据挖掘;刘学敏(1975-),男,山东烟台人,高级工程师,硕士,主要研究方向:大数据、云计算;张士波(1986-),男,山东聊城人,硕士,主要研究方向:大数据;李树仁(1972-),男,安徽亳州人,高级工程师,博士,主要研究方向:数据挖掘。
基金资助:
中国科学院“十三五”信息化专项（XXH13504-03）。

Abstract

Abstract: The high-level paper is one of the symbolic achievements of excellent scientific talents. Focusing on the "Web of Science (WOS)" hot research disciplines, on the basis of constructing the Neo4j semantic network graph of academic papers and mining active scientific research communities, the PageRank-based talent mining algorithm was used to realize the mining of outstanding scientific research talents in the scientific research communities. Firstly, the existing talent mining algorithms were studied and analyzed in detail. Secondly, combined with the WOS data, the PageRank-based talent mining algorithm was optimized and implemented by adding consideration factors such as the paper publication time factor, the author's order descending model, the influence of surrounding author nodes on this node, the number of citations of the paper. Finally, experiments and verifications were carried out based on the paper data of the communities of the hot discipline computer science in the past five years. The results show that community-based mining is more targeted, and can quickly find representative excellent and potential talents in various disciplines, and the improved algorithm is more effective and objective.

Key words: Web Of Science (WOS), Neo4j graph database, PageRank algorithm, talent mining

摘要： 高水平论文是优秀科技人才的标志性成果之一。聚焦“Web Of Science（WOS）”热点研究学科，在构建学术论文语义Neo4j网络图和挖掘出活跃科研社区基础上，利用PageRank人才挖掘算法实现对科研社区中优秀科研人才的挖掘。首先，对现有的人才挖掘算法进行详细研究和分析；其次，结合WOS论文数据对PageRank人才挖掘算法进行了优化设计和实现，加入了论文发表的时间因子、作者署名排序递减模型、周围作者节点对当前节点的影响、论文被引用量等多维度考量因素。最后，基于热点学科计算机科学某社区近五年的论文数据进行了实验和验证。结果表明，基于社区的挖掘更具有针对性，能够快速定位各学科代表性优秀和潜在人才，且改进后的算法对人才的发现更加客观有效。

关键词: Web Of Science, Neo4j图数据库, PageRank算法, 人才挖掘

CLC Number:

TP391

LI Chong, WANG Yuchen, DU Weijing, HE Xiaotao, LIU Xuemin, ZHANG Shibo, LI Shuren. PageRank-based talent mining algorithm based on Web of Science[J]. Journal of Computer Applications, 2021, 41(5): 1356-1360.

李翀, 王宇宸, 杜伟静, 何晓涛, 刘学敏, 张士波, 李树仁. 基于Web of Science的PageRank人才挖掘算法[J]. 计算机应用, 2021, 41(5): 1356-1360.

References

[1] 冯岭, 谢世博, 刘斌. 基于多层感知机的技术创新人才发现方法[J]. 计算机应用与软件,2019,36(7):26-31,42.(FENG L, XIE S B,LIU B. A technical innovation talents discovery method based on multi-layer perceptron[J]. Computer Applications and Software,2019,36(7):26-31,42.)
[2] 江艳萍, 夏琬钧, 赵颖梅, 等. 基于文献计量方法的全球潜力华人青年学者发现与评价策略研究[J]. 情报杂志,2019,38(7):178-183.(JIANG Y P,XIA W J,ZHAO Y M,et al. Discovery and evaluation strategy for the global potential Chinese young scholars:a research based on bibliometric method[J]. Journal of Intelligence,2019,38(7):178-183.)
[3] 王孟頔, 邰泳, 薛安荣. 基于Hadoop平台的人才发现与推荐系统研究[J]. 软件导刊,2014,13(1):4-6.(WANG M D,TAI Y, XUE A R. A discovery and recommendation system for talents based on Hadoop[J]. Software Guide,2014,13(1):4-6.)
[4] ZENG J,YU H. A scalable distributed Louvain algorithm for largescale graph community detection[C]//Proceedings of the 2018 IEEE International Conference on Cluster Computing. Piscataway:IEEE,2018:268-278.
[5] PARK N,KAN A,DONG X L,et al. Estimating node importance in knowledge graphs using graph neural networks[C]//Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York:ACM,2019:596-606.
[6] PARK N,KAN A,DONG X L,et al. MultiImport:inferring node importance in a knowledge graph from multiple input signals[C]//Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York:ACM,2020:503-512.
[7] 谢瑞霞, 李秀霞. 基于合著网络的作者影响力评价指标[J]. 情报理论与实践,2019,42(1):100-104.(XIE R X,LI X X. Evaluation indices of author influence based on collaboration network[J]. Information Studies:Theory and Application,2019, 42(1):100-104.)
[8] FREEMAN L C. Centrality in social networks conceptual clarification[J]. Social Networks,1979,1(3):215-239.
[9] BANGCHAROENSAP P,KOBAYASHI H,SHIMIZU N,et al. Two step graph-based semi-supervised learning for online auction fraud detection[C]//Proceedings of the 2015 Joint European Conference on Machine Learning and Knowledge Discovery in Databases,LNCS 9286. Cham:Springer,2015:165-179.
[10] BOUDIN F. A comparison of centrality measures for graph-based keyphrase extraction[C]//Proceedings of the 6th International Joint Conference on Natural Language Processing. Stroudsburg, PA:Association for Computational Linguistics,2013:834-838.
[11] 常雨萧. 复杂合著网络分析及可视化[D]. 重庆:重庆邮电大学,2017:31-40. (CHANG Y X. Complex co-authorship network analysis and visualization[D]. Chongqing:Chongqing University of Posts and Telecommunications,2017:31-40.)
[12] 娄策群. 社会科学评价的文献计量理论与方法[M]. 武汉:华中师范大学出版社,1999:10-14.(LOU C Q. Bibliometric Theory and Method of Social Science Evaluation[M]. Wuhan:Central China Normal University Press,1999:10-14.)
[13] 高伟. 基于InCites数据库的国家重点实验室科研成果评价研究[J]. 图书情报导刊,2018,3(2):57-65,73.(GAO W. Analysis on scientific research achievements evaluation of state key laboratory based on InCites database[J]. Journal of Library and Information Science,2018,3(2):57-65,73.)
[14] 张琳, 熊斯攀. 基于Neo4j的社交网络平台设计与实现[J]. 情报探索,2018(8):77-82.(ZHANG L,XIONG S P. Design and implementation of social network platform based on Neo4j[J]. Information Research,2018(8):77-82.)
[15] DE MEO P,FERRARA E,FIUMARA G,et al. Generalized Louvain method for community detection in large networks[C]//Proceedings of the 11th International Conference on Intelligent Systems Design and Applications. Piscataway:IEEE, 2011:88-93.
[16] CLAUSET A,NEWMAN M E J,MOORE C. Finding community structure in very large networks[J]. Physical Review, E, Statistical,Nonlinear,and Soft Matter Physics,2004,70(6 Pt 2):No. 066111.

PageRank-based talent mining algorithm based on Web of Science

基于Web of Science的PageRank人才挖掘算法

PDF

Knowledge

Abstract

Cite this article

share this article

References

Related Articles 4

Recommended Articles

Metrics

[1]	LIU Chao, TANG Zhengwang, YAO Hong, HU Chengyu, LIANG Qingzhong. Graph data processing technology in cloud platform [J]. Journal of Computer Applications, 2015, 35(1): 43-47.
[2]	WU Kai JI Xinsheng GUO Jinshi LIU Caixia. Influence maximization algorithm for micro-blog network [J]. Journal of Computer Applications, 2013, 33(08): 2091-2094.
[3]	LIANG Qiu-shi WU Yi-lei FENG Lei. User ranking algorithm for microblog search based on MapReduce [J]. Journal of Computer Applications, 2012, 32(11): 2989-2993.
[4]	. Improvement of PageRank algorithm by ant colony algorithm [J]. Journal of Computer Applications, 2009, 29(10): 2726-2728.