图书情报工作

图书情报工作 >

2013 , Vol. 57 >Issue 18: 122 - 126

DOI: https://doi.org/10.7536/j.issn.0252-3116.2013.18.021

知识组织

基于学术产出挖掘的用户兴趣建模研究

  • 姚晓娜 ,
  • 祝忠明 ,
  • 王思丽
展开
  • 中国科学院国家科学图书馆兰州分馆/中国科学院资源环境科学信息中心
姚晓娜,中国科学院国家科学图书馆兰州分馆/中国科学院资源环境科学信息中心馆员,E-mail:yaoxn@llas.ac.cn;祝忠明,中国科学院国家科学图书馆兰州分馆/中国科学院资源环境科学信息中心研究员,信息系统部主任;王思丽,中国科学院国家科学图书馆兰州分馆/中国科学院资源环境科学信息中心馆员。

收稿日期: 2013-07-24

  修回日期: 2013-09-02

  网络出版日期: 2013-09-20

基金资助

本文系中国科学院国家科学图书馆青年人才前沿领域基金项目“基于学术产出挖掘的用户兴趣建模研究”(项目编号:Y200081001)研究成果之一。

收起

User Interest Modeling Based on Literature Mining

  • Yao Xiaona ,
  • Zhu Zhongming ,
  • Wang Sili
Expand
  • Lanzhou Branch of the National Science Library/Scientific Information Center for Resources and Environment, CAS, Lanzhou 730000

Received date: 2013-07-24

  Revised date: 2013-09-02

  Online published: 2013-09-20

Fold

摘要

为了解决用户兴趣建模初期存在的冷启动问题,以科研用户公开发表的学术产出作为用户兴趣建模的数据源,采用文本挖掘和基于本体的模型表示技术进行用户建模,并提出一种通过实体关系表示用户兴趣的方法。该方法与使用单个关键词或实体的表示方法相比,语义信息更为丰富,能更好地描述用户兴趣。最后,将生成的用户兴趣本体实例存储到Sesame本体数据库中,支持通过SeRQL和SPARQL语言进行查询,实现了用户兴趣信息的语义化存储和检索。

关键词： 个性化服务; 用户兴趣建模; 文本挖掘; 本体; 实体关系对

本文引用格式

姚晓娜 , 祝忠明 , 王思丽 . 基于学术产出挖掘的用户兴趣建模研究[J]. 图书情报工作, 2013 , 57(18) : 122 -126 . DOI: 10.7536/j.issn.0252-3116.2013.18.021

Abstract

In order to solve the cold start problem existing at the beginning of user interest modeling, this paper puts the literature published by researchers as the data source of user interest modeling, and applies the technology of text mining and ontology modeling in user modeling, and proposes a method which describes user interest by using entity relationship pair. Compared to the method by using single keyword or entity, this method has more semantic information and can describe user interest better. Finally, the individuals of user interest ontology are stored into the Sesame ontology database and can be queried through SeRQL and SPARQL,and the semantic storage and retrieval of user interest information is implemented.

Key words： personalized service; user interest modeling; text mining; ontology; entity relationship pair

参考文献

[1] 郭海明, 刘昆雄. 数字图书馆个性化服务方式综述[J].津图学刊,2003, 21(6):33-36.
[2] 应晓敏. 面向Internet个性化服务的用户建模技术研究[D]. 长沙:国防科学技术大学, 2003.
[3] Cold start[EB/OL].[2013-08-14]. http://en.wikipedia.org/wiki/Cold_start.
[4] Zaiane O, Chen Jiyang, Goebel R. Mining research communities in bibliographical data[C]//Advances in Web Mining and Web Usage Analysis. Berlin: Springer-Verlag,2009:59-76.
[5] Hajian B, White T. Measuring semantic similarity using a multi-tree model[C]//Proceedings of the 9th Workshop on Intelligent Techniques for Web Personalization & Recommender Systems. Barcelona. CEUP Workshop Proceedings,2011:7-14.
[6] 孙雨生,刘伟,仇蓉蓉, 等.国内用户兴趣建模研究进展[J].情报杂志,2013,32(5):145-149,165.
[7] FOAF vocabulary specification[EB/OL].[2013-07-06]. http://xmlns.com/foaf/spec.
[8] SWEET Ontologies[EB/OL].[2013-07-06]. http://sweet.jpl.nasa.gov/sweet.
[9] SWRC Ontology[EB/OL].[2013-07-06]. http://ontoware.org/swrc.
[10] DBPedia Ontology[EB/OL].[2013-07-06]. http://wiki.dbpedia.org/Ontology.
[11] The weighted interests vocabulary[EB/OL].[2013-07-06].http://smiy.sourceforge.net/wi/spec/weightedinterests.html.
[12] Web of science Web services[EB/OL].[2013-07-06].http://wokinfo.com/products_tools/products/related/webservices.
[13] GATE, a general architecture for text engineering[EB/OL].[2013-07-06].http://gate.ac.uk.
[14] The Stanford Parser[EB/OL].[2013-07-06]. http://nlp.stanford.edu/software/lex-parser.shtml.
[15] Stanford dependencies[EB/OL].[2013-07-06]. http://nlp.stanford.edu/software/stanford-dependencies.shtml.
[16] 潘建国. 基于语义的用户建模技术与应用研究[D].上海:上海大学, 2008.
[17] OpenRDF.org[EB/OL].[2013-07-06]. http://www.openrdf.org.
Options
文章导航

/

〈 〉