Analysis Of Folksonomy System Users’ Behavioral Characteristics

In the age of Web2.0, Folksonomy System is widely used in a variety of social network sites, such as:Delicious, Douban, Sina microblog, etc. With the wide application and development of Folksonomy system in the social network websites, more ordinary Internet users are participating in the making and releasing of the Internet information.Folksonomy system is a civilian classification, whose classification labels have the advantage of individual spontaneous definition and classification openly-sharing labels, but have the disadvantage of semantic ambiguity, inaccuracy, indiscretion, which leads to the low efficiency of user information discovery and share. Additionally, the individual label spells errors, labels in Chinese word segmentation structure ambiguity and the obvious difference of semantic cognition in different language context need to be resolved. Facing the development bottleneck of folksonomy system, we resort to the traditional classification. The traditional taxonomy centered on the subject, after years of development and practical application, its architecture has been very mature and perfect. Using the traditional taxonomy, we optimize and improve folksonomy, so as to improve the quality and efficiency of the organization and classification of network information, that is, to be able to apply the semantic relations of Chinese Thesaurus to extend user’s label, to play a role of recommended and retrieval label, to analyse user label data in real time, to study the degree of user preferences, so as a data source of thesaurus vocabulary update.First of all, This paper introduces the background, purpose and meaning of the research. On the basis of collecting date of users, labels, resources from Delicious website which is a folksonomy system, the paper analyses characteristics of delicious labels. Then,it carries out a comparative analysis on the Chinese tags (Education) and the keywords(Education) from "Chinese Classification Thesaurus", explores the possibility and technical implementation methods of tags and keywords integration, and proposes the theoretical models and methods of learning and integration from each other. Then, on the basis of the analysis of user distribution and resource types, by using social network analysis, the paper clusters analysis of user base, resource class, label set, to find the core users, core resources, core label; then, on the basis of classification analysis (Analytic Hierarchy Process) and clustering analysis, on the combination of social behavior knowledge, the paper makes a detailed analysis of how to choose resources, and of how to choose a label, etc. Then, the paper makes an example by analyzing an active user’s specific behavior and preferences from the resource sharing situation, the label features and followings on other users, etc. Finally, we summarize the main work and conclusions, and put forward the paper’s shortcomings and the subject questions in further research.