一种融合科研人员标签的学术论文推荐方法

doi:10.11896/jsjkx.190300121

计算机科学 ›› 2020, Vol. 47 ›› Issue (2): 51-57.doi: 10.11896/jsjkx.190300121

• 数据库&大数据&数据科学 • 上一篇下一篇

一种融合科研人员标签的学术论文推荐方法

吴磊¹,岳峰²,王含茹³,王刚³

(合肥工业大学人事处合肥230009)¹;
(肥工业大学计算机与信息学院合肥230009)²;
(合肥工业大学管理学院合肥230009)³

收稿日期:2019-03-25 出版日期:2020-02-15 发布日期:2020-03-18
通讯作者: 吴磊(leewu79@hotmail.com)
基金资助:
国家自然科学基金(71471054,91646111);教育部人文社科基金(18YJC870025);安徽省自然科学基金(1608085MG150)

Academic Paper Recommendation Method Combined with Researcher Tag

WU Lei¹,YUE Feng²,WANG Han-ru³,WANG Gang³

(Personnel Department,Hefei University of Technology,Hefei 230009,China)¹;
(School of Computer Science and Information Engineering,Hefei University of Technology,Hefei 230009,China)²;
(School of Management,Hefei University of Technology,Hefei 230009,China)³

Received:2019-03-25 Online:2020-02-15 Published:2020-03-18
About author:WU Lei,born in 1979,Ph.D,doctorial student,lecturer.His main research interests include recommender system and so on.
Supported by:
This work was supported by the National Natural Science Foundation of China (71471054, 91646111), Ministry of Education of Humanities and Social Science Foundation (18YJC870025) and Natural Science Foundation of Anhui Province, China (1608085MG150).

摘要/Abstract

摘要： 近年来,科研社交网络的兴起在一定程度上转变了科研人员原有的科研交流合作模式,深受科研人员的欢迎;然而,科研社交网络上激增的研究成果数量使得科研人员很难找到自己真正感兴趣的学术论文。因此,为科研人员推荐其感兴趣的学术论文,成为一项重要任务。考虑到科研社交网络中科研人员阅读论文数据的特殊性,文中从单类协同过滤角度考虑科研社交网络中的论文推荐问题。一方面,利用科研人员的标签信息进行更精确的负例抽取,并在此基础上考虑科研人员的活跃度以确定负例数量;另一方面,基于添加完负例的科研人员-学术论文评分矩阵进行概率矩阵分解,在概率矩阵分解阶段融合科研人员标签关联矩阵以及论文相似度信息来进行约束,以缓解数据稀疏对最终结果的不利影响。最后,在科研社交网络“科研之友”上进行实验,采用准确率、召回率、平均准确率、平均倒数排名这4项评价指标对推荐结果的准确性及推荐排序进行验证。实验结果表明,所提方法相较于主流方法取得了更好的结果,在准确率指标上提升了4.19%,验证了所提方法将论文推荐考虑为单类协同过滤问题的有效性,以及社会化信息对推荐的有效辅助作用;并且,所提方法在推荐系统中具有良好的可扩展性,能够在科研社交网络中为科研人员进行有效的论文推荐。

关键词: 单类协同过滤, 概率矩阵分解, 科研人员标签, 科研社交网络, 论文推荐

Abstract: In recent years,the rise of scientific social networks has changed the original mode of exchanges and cooperation among researchers to some extent,which makes scientific social networks well received by researchers.With the surge of research fin-dings on scientific social networks,it’s difficult for researchers to find research papers they are really interested in.Consequently,it becomes an important task to recommend the papers that researchers are interested in.Considering the particularity of resear-chers’ reading data,this paper conducted paper recommen-dation from the perspective of one class collaborative filtering.On the one hand,researchers’ tag information is used to extract negative cases precisely;on the other hand,based on the researcher-paper matrix with negative instances incorporated,the researchers-tag matrix and papers’ similarity information are jointly integrated into the probability matrix factorization,to alleviate the data sparsity problem.Finally,experiments were carried out on a scientific social network,ScholarMate.Four evaluation metrics,namely precision,recall,MAP,and MRR,were adopted to verify the recommendation accuracy as well as the recommendation order.The experimental results show that the proposed method performs betterthan the baselines with an improvement of 4.19% in terms of the precision,which demonstrate the effectiveness of considering the paper recommendation on scientific social networks as a one-class collaborative filtering problem,the effectiveness of introducing extra social information to improve the recommendation results,and the scalability of the proposed method.

Key words: One class collaborative filtering, Paper recommendation, Probabilistic matrix factorization, Researcher tag, Scientific social networks

中图分类号:

TP391.3

吴磊,岳峰,王含茹,王刚. 一种融合科研人员标签的学术论文推荐方法[J]. 计算机科学, 2020, 47(2): 51-57. https://doi.org/10.11896/jsjkx.190300121

WU Lei,YUE Feng,WANG Han-ru,WANG Gang. Academic Paper Recommendation Method Combined with Researcher Tag[J]. Computer Science, 2020, 47(2): 51-57. https://doi.org/10.11896/jsjkx.190300121

参考文献

[1]LI L L,WU X N.A Study of Scientific Social Network’s Development and Trend.Research on Library Science[J].Research on Library Science,2013,10(1):36-41.
[2]WEI J,HE D Q.User participation in an academic social net-working service:A survey of open group users on M endeley[J].Journal of the American Society for Information Science and Technology,2015,66(5):890-904.
[3]SUGIYAMA K,KAN M Y.Scholarly paper recommendation via user’s recent research interests[C]∥Proceedings of the 10th annual joint conference on Digital libraries.Gold Coast,Queensland,Australia,2010:29-38.
[4]PANDEY A K,RAJPOOT D S.Resolving Cold Start problem in recommendation system using demographic approach[C]∥2016 International Conference on Signal Processing and Communication (ICSC).IEEE,2016:213-218.
[5]WANG G,HE X,ISHUGA C I J K.HAR-SI:A novel hybrid article recommendation approach integrating with social information in scientific social network[J].Knowlwdge Based Systems,2018,148(9):85-99.
[6]PHILIP S,SHOLA P B,JOHN A O.Application of content-based approach in research paper recommendation system for a digital library[J].International Journal of Advanced Computer Science and Applications,2014,5(10):37-40.
[7]TSOLAKIDIS A.Research publication recommendation system based on a hybrid approach[C]∥Proceedings of the 20th Pan-Hellenic Conference on Informatics.ACM,New York,USA,2016:78.
[8]VIVACQUA A S,OLIVEIRA J,DE SOUZA J M.i-ProSE:inferring user profiles in a scientific context[J].The Computer Journal,2009,52(7):789-798.
[9]MARTÍN G H,SCHOCKAERT S,CORNELIS C,et al.Using semi-structured data for assessing research paper similarity[J].Information Sciences,2013,221(35):245-261.
[10]HONG K,JEON H,JEON C.Personalized research paper rec-ommendation system using keyword extraction based on userprofile[J].Journal of Convergence Information Technology,2013,8(16):106.
[11]BOGERS T,VAN DEN BOSCH A.Recommending scientific articles using citeulike[C]∥Proceedings of the 2008 ACM Confe-rence on Recommender Systems.Lausanne,Switzerland,2008:287-290.
[12]WANG C,BLEI D M.Collaborative topic modeling for recommending scientific articles[C]∥Proceedings of the 17th ACM SIGKDD international conference on Knowledge discovery and data mining.San Diego,California,USA,2011:448-456.
[13]LEE D H,BRUSILOVSKY P.Using self-defined group activities for improvingrecommendations in collaborative tagging systems[C]∥Proceedings of the fourth ACM Conference on Re-commender Systems.Barcelona,Spain,2010:221-224.
[14]KIM H K,OH H Y,GU J C,et al.Commenders:A recommendation procedure for online book communities[J].Electronic Commerce Research and Applications,2011,10(5):501-509.
[15]PAN R,ZHOU Y,CAO B,et al.One-class collaborative filtering[C]∥2008 Eighth IEEE International Conference on Data Mi-ning.Antwerp,Belgium,2008:502-511.
[16]SUN J,WANG G,CHENG X,et al.Mining affective text to improve social media item recommendation[J].Information Processing & Management,2015,51(4):444-457.
[17]PAPPAS N,POPESCU-BELIS A.Sentiment analysis of user comments for one-class collaborative filtering over ted talks[C]∥Proceedings of the 36th International ACM SIGIR Confe-rence on Research and Development in Information Retrieval.Dublin,Ireland,2013:773-776.
[18]HU Y,KOREN Y,VOLINSKY C.Collaborative filtering for implicit feedback datasets[C]∥2008 Eighth IEEE International Conference on Data Mining.Pisa,Italy,2008:263-272.
[19]JIANG M,CUI P,LIU R,et al.Social contextual recommendation[C]∥Proceedings of the 21st ACM international conference on Information and knowledge management.Maui,HI,USA,2012:45-54.
[20]CHEN K,CHEN T,ZHENG G,et al.Collaborative personalized tweet recommendation[C]∥Proceedings of the 35th international ACM SIGIR conference on Research and development in information retrieval.Portland,Oregon,USA,2012:661-670.
[21]LI Y,HU J,ZHAI C X,et al.Improving one-class collaborative filtering by incorporating rich user information[C]∥Procee-dings of the 19th ACM international conference on Information and knowledge management.Toronto,Ontario,Canada,2010:959-968.
[22]KAYA H,ALPASLAN F N.Using social networks to solve data sparsity problem in one-class collaborative filtering[C]∥2010 Seventh International Conference on Information Technology:New Generations.Las Vegas,NV,USA,2010:249-252.
[23]RESNICK P,VARIAN H R.Recommender systems[J].Communications of the ACM,1997,40(3):56-59.
[24]SCHAFER J B,FRANKOWSKI D,HERLOCKER J,et al.Collaborative filtering recommender systems[M]∥The adaptive web.Berlin:Springer,2007:291-324.
[25]LI H.Learning to rank for information retrieval and natural language processing[J].Synthesis Lectures on Human Language Technologies,2011,4(1):1-113.
[26]ZHANG S,WANG W,FORD J,et al.Using singular value decomposition approximation for collaborative filtering[C]∥Se-venth IEEE International Conference on E-Commerce Technology (CEC05).Munich,Germany,2005:257-264.
[27]MNIH A,SALAKHUTDINOV R R.Probabilistic matrix fac-torization[C]∥Advances in neural information processing systems.Vancouver,BC,Canada,2008:1257-1264.
[28]PAPPAS N,POPESCU-BELIS A.Adaptive sentiment-aware one-class collaborative filtering[J].Expert Systems with Applications,2016,43(9):23-41.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed

一种融合科研人员标签的学术论文推荐方法

Academic Paper Recommendation Method Combined with Researcher Tag

PDF (PC)

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 4

Metrics

本文评价

推荐阅读 0

[1]	田贤忠,沈杰. 大数据环境下基于概率矩阵分解的个性化推荐 Personalized Recommendation Based on Probabilistic Matrix Factorization in Big Data Environment 计算机科学, 2017, 44(Z6): 438-441. https://doi.org/10.11896/j.issn.1002-137X.2017.6A.098
[2]	李改,陈强,李磊,潘进财. 融合社交网络的单类个性化协同排序算法 One-class Personalized Collaborative Ranking Algorithm Incorporating Social Network 计算机科学, 2017, 44(2): 88-92. https://doi.org/10.11896/j.issn.1002-137X.2017.02.011
[3]	吴燎原,蒋军,王刚. 科研社交网络中基于联合概率矩阵分解的科技论文推荐方法研究 Study of Scientific Paper Recommendation Method Based on Unified Probabilistic Matrix Factorization in Scientific Social Networks 计算机科学, 2016, 43(9): 213-217. https://doi.org/10.11896/j.issn.1002-137X.2016.09.042
[4]	李斌,张博,刘学军,章玮. 基于Jaccard相似度和位置行为的协同过滤推荐算法 Collaborative Filtering Recommendation Algorithm Based on Jaccard Similarity and Locational Behaviors 计算机科学, 2016, 43(12): 200-205. https://doi.org/10.11896/j.issn.1002-137X.2016.12.036