您的位置:山东大学 -> 科技期刊社 -> 《山东大学学报(理学版)》

山东大学学报(理学版) ›› 2016, Vol. 51 ›› Issue (5): 94-101.doi: 10.6040/j.issn.1671-9352.1.2015.E15

• • 上一篇    下一篇

基于知识脉络的科技论文推荐

谭红叶1,要一璐1,梁颖红2   

  1. 1. 山西大学计算机与信息技术学院, 山西 太原 030006;2.金陵科技学院软件工程学院, 江苏 南京 211169
  • 收稿日期:2015-09-25 出版日期:2016-05-20 发布日期:2016-05-16
  • 作者简介:谭红叶(1971— ),女,博士,副教授,研究方向为NLP、信息抽取、自动问答等.E-mail: hytan-2006@126.com
  • 基金资助:
    国家高技术研究发展计划(863计划)项目(2015AA015407);国家自然科学青年基金资助项目(61100138,61403238);山西省自然科学基金资助项目(2011011016-2,2012021012-1);山西省回国留学人员科研项目(2013-022);山西省高校科技开发项目(20121117);山西省2012年度留学回国人员科技活动择优项目

Knowledge vein-based recommendation of academic papers

TAN Hong-ye1, YAO Yi-lu1, LIANG Ying-hong2   

  1. 1.School of Computer and Information Technology, Shanxi University, Taiyuan 030006, Shanxi, China;
    2.School of Software Engineering, Jinling Institute of Technology, Nanjing 211169, Jiangsu, China
  • Received:2015-09-25 Online:2016-05-20 Published:2016-05-16

摘要: 将关键词作为作者兴趣标识,利用论文文本中关键词之间的同义关系、上下位关系和共现关系构建成知识脉络,并结合基于内容过滤的方法对作者进行科技论文推荐。该方法将关键词向量之间的平均最大语义相似度作为作者和论文基于知识脉络的相似度,考虑了同义和上下位关系两种语义关系,并在此基础上加入了关键词的共现关系进行论文推荐。实验结果表明该方法的推荐准确率和召回率明显提升。

关键词: 知识脉络, 兴趣模型, 论文推荐, 关系抽取

Abstract: This paper proposed a method of scientific papers recommendation based on knowledge vein, which identified the authors of paper with their keywords and build a knowledge vein by using the synonymy, hyponymy and co-occurrence relationship of keywords. This method recommended academic papers for authors combined with CBF and knowledge vein. This method definition that similarity between authors and papers is the average maximum semantic similarity of the keyword vectors. Currently this article considered two kinds of semantic relations, synonymous and hyponymy. In addition, the relation of co-occurrence also was considered. The results showed that this method can provide more accurate and credible scientific paper recommendation service for authors.

Key words: knowledge vein, interest model, relation extraction, paper recommendation

中图分类号: 

  • TP391
[1] BOLLACKER K D, LAWRENCE S, GILES C L. CiteSeer: an autonomous web agent for automatic retrieval and identification of interesting publications[C] //Proceedings of the 2nd International Conference on Autonomous Agents. New York: ACM, 1998:116-123.
[2] LOPS P, GEMMIS M, SEMERARO G. Content-based recommender systems: state of the art and trends[C] //Francesco Ricci, Lior Rokach, Bracha Shapira, et al. Recommender Systems Handbook. Berlin: Springer, 2011:73-105.
[3] Joeran Beel, Bela Gipp, Stefan Langer, et al. Research-paper recommender systems: a literature survey [EB/OL]. [2015-04-02].http://link.springer.com/article/10.1007/s00799-015-0156-0
[4] 王位春, 张铭. 基于语义概念相似度的科技文献推荐算法[EB/OL].(2008-07-04)[2015-03-25]. http://www.paper.edu.cn/releasepaper/content/200807-147. WANG Weichun, ZHANG Ming. Recommendation algorithm for scientific and technology literature based on semantic concept similarity[EB/OL].(2008-07-04)[2015-03-25]. http://www.paper.edu.cn/releasepaper/content/200807-147.
[5] OHTA M, HACHIKI T, TAKASU A. Related paper recommendation to support online-browsing of research papers[C] //Proceedings of the 4th International Conference on Applications of Digital Information and Web Technologies(ICADIWT). New York: IEEE, 2011:130-136.
[6] REN Xiang, LIU Jialu, YU Xiao, et al. Cluscite: effective citation recommendation by information network-based clustering[C] //Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York: ACM, 2014:821-830.
[7] Dohyun Kim, Bong-Jin Yum. Collaborative filtering based on iterative principal component analysis[J]. Expert Systems with Applications, 2005, 28(4): 823-830.
[8] XI Yunjiang, DANG Yanzhong, WU Jiangning. The complex network modeling method and its application to the knowledge system[C] //Proceedings of the 1st World Congress of the International Federation for Systems Research: The New Roles of Systems Sciences for a Knowledge-based Society. Japan: JAIST Press, 2005: 426-431.
[9] 席运江,党延忠. 基于知识网络的专家领域知识发现及表示方法[J]. 系统工程, 2005, 23(8): 110-115. XI Yunjiang, DANG Yanzhong. The discovery and representation methods of expert domain knowledge based on knowledge network[J]. Systems Engineering, 2005, 23(8):110-115.
[10] John L Gordon. Creating knowledge maps by exploiting dependent relationships [J]. Knowledge Based Systems, 2000, 13(4): 71-79.
[11] John L Gordon, Lee Jorgensen. Learning support using knowledge structure maps [EB/OL]. [2015-05-01]. http://akri.org/rese-arch/papers/pdf/Learning-Support-using-Knowledge-Structure-Maps.pdf.
[12] Luca Stefanutti, Mathieu Koppen. A procedure for the incremental construction of a knowledge space [J]. Journal of Mathematical Psychology, 2003, 47: 265-277.
[13] Michael James Young. Quantifying the characteristics of knowledge structure representations: lattice theoretic framework [EB/OL].[2015-03-12].http://www.cse.ucla.eduPReportsPTECH479.PDF.
[14] CHEN C, PAUL R J. Visualizing a knowledge domain's intellectual structure [J]. Computer, 2001, 34(3):65-71.
[15] 赵华,林政,方艾,等.一种基于知识树的推荐算法及其在移动电子商务上的应用[J]. 电信科学, 2011, 27(6):54-58. ZHAO Hua, LIN Zheng, FANG Ai, et al. Knowledge tree based recommendation algorithm with its applications to mobile e-commerce[J]. Telecommunications Science, 2011, 27(6):54-58.
[16] 魏瑞斌.基于共词网络的学术期刊知识图谱构建[J]. 情报杂志, 2011, 30(10):36-42. WEI Ruibin. The mapping knowledge domain of scholarly journal based on the co-word network[J]. Journal of Intelligence, 2011, 30(10):36-42.
[17] 陆勇,章成志,侯汉清. 基于百科资源的多策略中文同义词自动抽取研究[J]. 中国图书馆学报, 2010, 36(1):56-62. LU Yong, ZHANG Chengzhi, HOU Hanqing. Using multiple hybrid strategies to extract Chinese synonyms from encyclopedia resources[J]. Journal of Library Science in China, 2010, 36(1):56-62.
[18] 张颖杰,李斌,陈家骏,等.基于词典信息的先秦汉语全文词义标注方法研究[J]. 中文信息学报, 2012, 26(3):65-71. ZHANG Yingjie, LI Bin, CHEN Jiajun, et al. A study in dictionary-based all-word word sense disambiguation for Pre-Qin Chinese[J]. Journal of Chinese Information Processing, 2012, 26(3):65-71.
[19] 张旸,路荣,杨青.微博客中转发行为的预测研究[J]. 中文信息学报, 2012, 26(4):109-114. ZHANG Yang, LU Rong, YANG Qing. Predicting retweeting in microblogs[J]. Journal of Chinese Information Processing, 2012, 26(4):109-114.
[20] 廉涛,马军,王帅强,等. LDA-CF:一种混合协同过滤方法[J]. 中文信息学报, 2014, 28(2):129-135. LIAN Tao, MA Jun, WANG Shuaiqiang, et al. LDA-CF: a mixture model for collaborative filtering[J]. Journal of Chinese Information Processing, 2014, 28(2):129-135.
[21] 汤青,吕学强,李卓. 本体概念间上下位关系抽取研究[J]. 微电子学与计算机, 2014(6):68-71. TANG Qing, LÜ Xueqiang, LI Zhuo. Research on domain ontology concept hyponymy relation extraction[J]. Microelectronics & Computer, 2014(6):68-71.
[22] 李熙. 基于六度分割理论和中心度识别微博网络的关键人物[D]. 成都:西华大学, 2013. LI Xi. Based in the six degrees of separation and centrality to identify the key figure in the Micro-blog[D]. Chengdu: Xihua University, 2013.
[23] 黄泽明. 基于主题模型的学术论文推荐系统研究[D]. 大连:大连海事大学, 2013. HUANG Zeming. Research on recommended system of scholar paper based on topic model[D]. Dalian: Dalian Maritime University, 2013.
[1] 孙建东,顾秀森,李彦,徐蔚然. 基于COAE2016数据集的中文实体关系抽取算法研究[J]. 山东大学学报(理学版), 2017, 52(9): 7-12.
[2] 杨震,司书勇,李超阳. 基于用户隐式兴趣模型的信息推荐[J]. 山东大学学报(理学版), 2017, 52(1): 15-22.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!