基于标签相似度计算的学术圄构建方法-计算机科学.pdfVIP

第 43 卷第9 期 计算机科学 Vo1. 43 No.9 2016 年 9 月 Computer Science Sep 2016 基于标签相似度计算的学术圄构建方法 傅城州1 汤庸1 贺超波2 王津凌1 袁成哲1 (华南师范大学计算机学院 广州 510631) 1 (仲皑农业工程学院信息科学与技术学院 广州 510225)2 摘 要 为面向学者的社交网络系统中的用户构建学术圈，对促进学者之间的交流具有重要的应用价值。根据学者 之间的共同属性进行相似度计算，形成学术领域相似和研究课题相近的学术圈，能让学者们更加紧密和频繁地协同合 作。提出了利用学者的学术信息提取代表个人特征的学术标签，并对不同类别标签的权重进行衡量，再通过相似度计 算和聚类算法构建学术圈的方法。通过抓取学者社交网络平台 SCHOLAT 公开的学者信息进行实验，进而验证所提 方法的可靠性和实用性。 关键词 社交网络，标签，相似度计算，聚类算法，学术圈 中固法分类号 TP311 文献标识码 A DOI 10. 11896/j. issn. 1002-137X. 2016. 9. 009 Construction Method of Academic Circle ßased on Label Similarity Computation FU Cheng-zhou1 TANG Yong1 HE Chao-b02 WANG Jin-ling1 YUAN Cheng-zhe1 (School of Computer Science ,South China Normal University ,Guangzhou 510631 ,China) 1 (Sch口。1 of Information Science and Technology ,Zhongkai University of Agriculture and Engineering ,Guangzhou 510225 ,China)2 Abstract Constructing academic circles for users in the scholar-oriented social network system has important applica tion values for promoting exchanges among scholars. Similarity computation is done based on the common properties of scholars ,constituting academic circles with similar academic field and research subject ,allowing scholars to collaborate more closely and frequently. This paper proposed a method which uses scholars of the academic information to extract the personal characteristics of academic labels ,and measures the weight of different class labels. Then through the simi larity computation and clustering algorithm ,the academic circle can be constructed. By crawling the public information on the academic social network platform