基于共被引理论的在线音乐网站歌手分类研究  

Research on Classification of Singers in Online Music Websites Based on Co-citation Theory

作　　者：王贤文[1,2] 胡志刚[1,2] 丁堃[1,2] 刘则渊[1,2] 

机构地区：[1]大连理工大学人文学院,大连116085 [2]大连理工大学-德雷塞尔大学知识可视化与科学发现联合研究所,大连／费城

出　　处：《情报学报》2011年第5期471-478,共8页Journal of the China Society for Scientific and Technical Information

基　　金：教育部高等学校博士学科点专项科研基金（批准号20090041110001）; 国家自然科学基金项目（批准号70773015）

摘　　要：文献计量学中的共被引分析是一种基于参考文献的共现关系而建立共被引网络的分析方法,可用来展现引文的结构和聚类关系。将文献计量学中的共被引思想拓展到对互联网用户音乐收藏行为的分析中,进行音乐分类,是一种新的尝试。通过从某在线音乐网站随机选择500名网络用户作为研究样本,从他们的音乐收藏夹中提取歌手的共被引次数矩阵,计算Jaccard系数矩阵,进一步进行共被引分析,利用社会网络分析工具绘制歌手共被引网络。可以将这种方法进一步拓展到其他互联网文化消费领域,改进互联网文化消费的可视化搜索,挖掘互联网用户的消费兴趣,增强用户体验。The co-citation analysis in bibliometrics is a method to display the structure and classification of the citation references based on their cooccurrence relations.Songs/singers co-collection relationship by online music web users is referred from the co-citation analysis theory in bibliometrics field.Based on this relationship,the authors get the singers co-collection network,which can serve as a new approach to classify singers.In this paper,the authors select 500 web users randomly from one online music website as research samples,extract the singers co-collection matrix from the users＇ music favorites,then make co-collection analysis and network analysis when Jaccard matrix calculated,This method could also be expanded into other Internet culture consumption field,and will be helpful for improving the visualization search technologe,digging the the interests of Internet user,and eventually enhancing the Internet user experience.

关 键 词：音乐分类 音乐可视化搜索 共被引 网络计量 

分 类 号：G301[文化科学]