A Method for Ontology Construction derived from Folksonomy
This paper proposes a novel method for constructing ontology derived from folksonomy. Compared with traditional ones,this method is high in speed and costs less,and most important of all, it is appropriate for ontology construction of emerging areas thanks to folksonomy covering the latest concepts. The concrete process is as follows. First of all,overlap similarity is used to measure similarity between co-occurrence tags and Spectral Clustering Algorithm (SCA) is applied to cluster tags with semantic relations. Moreover,another algorithm is provided to obtain hierarchical structure of tags by running SCA repeatedly. Finally,online ontology resource WordNet is employed to add definitions and other semantic relations between tags to finish the work.
folksonomy ontology construction spectral clustering algorithm (SCA)
Jiyuan He Yongxiang Dou Dongsu Liu
Department of Information Management,Xidian University,Xian,710071,China
国际会议
The Tenth Wuhan International Conference on E-Business(第十届武汉电子商务国际会议)
成都
英文
503-508
2011-05-13(万方平台首次上网日期,不代表论文的发表时间)