基于学术水平聚类的科研合作者推荐模型

doi:10.3778/j.issn.1002-8331.2103-0540

摘要/Abstract

摘要： 针对现有科研合作者推荐模型一般不考虑目标学者与推荐学者间学术水平的差距,导致合作关系难以建立的问题，提出一种基于学术水平聚类的合作者推荐模型，为目标学者推荐最合适合作者（fitting collaborator recommendation，FCR）。该模型先使用K-means算法对合作网络中的学者按照学术水平特征进行聚类，在同一水平簇别中建立合作网络，利用链路预测算法中的Katz指标对网络中的节点进行相似度计算，对学者们的研究主题进行提取，在网络的可达性，学术水平是否相近以及研究主题相似度三个方面进行综合考虑并进行Top-N推荐。实验结果表明，相比于其他模型，提出的基于学术水平聚类的合作者推荐模型相比于其他推荐模型均有着较优的表现，在推荐的准确率、召回率以及F1指数上分别提高了5.3%、2.5%、4%。并且在推荐的合作学者与目标学者的学术水平匹配性方面平均提高了37%。

关键词: 合作者推荐, 社会网络, K-means聚类, Katz指标

Abstract: In order to solve the problem that the existing collaborator recommendation model does not consider the academic level gap between the target scholar and the recommended scholar, this paper proposes an collaborator recommendation model based on academic level clustering , recommend the most suitable collaborators for the target scholars（fitting collaborator recommendation, FCR）. FCR uses the K-means algorithm to cluster the scholars in the cooperative network according to the characteristics of the academic level, and then establishes the cooperative network in the same level category, and uses the Katz indicator in the link prediction algorithm to perform similarity to the nodes in the network, and calculates and extracts the research topics of scholars. Finally, the accessibility of the node in the network, whether the academic level is similar or not, and the similarity of research topics are comprehensively considered, comprehensively calculate their recommendation scores and make Top-N recommendations. Compared with other recommendation models, the proposed model has better performance in accuracy, recall and F1 index, which are 5.3%, 2.5% and 4% higher on average. In addition, the academic level matching between the other models has been improved by 37% on average.

Key words: collaborator recommend, social network, K-means, Katz index

秦红武, 赵猛, 马秀琴, 赵德志, 闫文英. 基于学术水平聚类的科研合作者推荐模型[J]. 计算机工程与应用, 2022, 58(21): 172-181.

QIN Hongwu, ZHAO Meng, MA Xiuqin, ZHAO Dezhi, YAN Wenying. Collaborator Recommendation Model Based on Academic Level Clustering[J]. Computer Engineering and Applications, 2022, 58(21): 172-181.

参考文献

[1] LEE S，BOZEMAN B.The impact of research collaboration on scientific productivity[J].Social Studies of Science，2005，35（5）：673-702.
[2] KONG X，JIANG H，YANG Z，et al.Exploiting publication contents and collaboration networks for collaborator recommendation[J].PloS One，2016，11（2）：e0148492.
[3] PRADHAN T，PAL S.A multi-level fusion based decision support system for academic collaborator recommendation[J].Knowledge-Based Systems，2020，197：105784.
[4] PU S S.Expert recommendation model in scientific and technical collaboration based on complementary knowledge[J].Information Studies：Theory & Application，2018，41（8）：96-101.
[5] LI C，TANG Y，XIAO Z，et al.Influential scholar recommendation model in academic social network[J].Journal of Computer Applications，2020，40（9）：2594.
[6] ZHOU X，DING L，LI Z，et al.Collaborator recommendation in heterogeneous bibliographic networks using random walks[J].Information Retrieval Journal，2017，20（4）：317-337.
[7] LIU X，DU X C，KANG W J.Research on co-author recommender model based on homogeneous coauthor networks[J].Journal of Changsha University，2017，31（2）：62-66.
[8] XIONG H X，YANG X P，et al，Scholars recommend research based on academic competence and collaborative networks[J].Information Science，2019，37：71-78.
[9] CHEN K H，HAN P P，WU J.User clustering based social network recommendation[J].Chinese Journal of Computers，2013（2）：13.
[10] REN X Y，SONG M N，SONG J D.Context-aware point-of-interest recommendation in location-based social networks[J].Chinese Journal of Computers，2017，40（4）：824-841.
[11] GUNS R，ROUSSEAU R.Recommending research collaborations using link prediction and random forest classifiers[J].Scientometrics，2014，101（2）：1461-1473.
[12] WAHID-UL-ASHRAF A，BUDKA M，MUSIAL K.How to predict social relationships—Physics-inspired approach to link prediction[J].Physica A：Statistical Mechanics and its Applications，2019，523：1110-1129.
[13] 钱付兰，杨强，马闯，等.加权好友推荐模型链路预测算法[J].计算机科学与探索，2019，13（3）：383-393.
QIAN F L，YANG Q，MA C，et al.Link prediction algorithm of weighted friend recommendation model[J].Journal of Frontiers of Computer Science and Technology，2019，13（3）：383-393.
[14] ZENG S.Link prediction based on local information considering preferential attachment[J].Physica A：Statistical Mechanics and its Applications，2016，443：537-542.
[15] WU Z，LIN Y，WANG J，et al.Link prediction with node clustering coefficient[J].Physica A：Statistical Mechanics and its Applications，2016，452：1-8.
[16] YANG Y，ZHANG J，ZHU X，et al.Link prediction via significant influence[J].Physica A：Statistical Mechanics and its Applications，2018，492：1523-1530.
[17] ZHANG P，WANG F，WANG X，et al.The reconstruction of complex networks with community structure[J].Scientific Reports，2015，5（1）：1-11.
[18] LIU W，LU L.Link prediction based on local random walk[J].EPL（Europhysics Letters），2010，89（5）：58007.
[19] TIAN B J，DU X J.Research of hybrid collaborative filtering optimized technology in cloud computing[J].Application Research of Computers，2018（7）.
[20] KONG X，JIANG H，WANG W，et al.Exploring dynamic research interest and academic influence for scientific collaborator recommendation[J].Scientometrics，2017，113（1）：369-385.
[21] LI S B，ZHANG Y W，LIU J H，et al.Recommendation model based on public neighbor sorting and sampling of knowledge graph[J].Journal of Electronics & Information Technology，2021，43（12）：3522-3529.
[22] WANG W，LIU J，TANG T，et al.Attributed collaboration network embedding for academic relationship mining[J].ACM Transactions on the Web，2020，15（1）：1-20.
[23] TANG J，WU S，SUN J M，et al.Cross-domain collaboration recommendation[C]//Proceedings of the 18th ACM SIGKPD International Conference on Knowledge Discovery and Data Mining，2012：1285-1293.
[24] GUO Y，CHEN X.Cross-domain scientific collaborations prediction using citation[C]//2013 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining，2003.
[25] WANG X.Research on methods of cross-domain recommendation with transfer learning[D].Hangzhou：Hangzhou Dianzi University，2015.
[26] WANG J，LI S J，YANG S，et al.A new transfer learning model for cross-domain recommendation[J].Chinese Journal of Computers，2017，40：2367-2380.