A type of Web search method or algorithm which leverages all kinds of user interaction data, such as social tags, query logs. It is a promising research direction and successful search practice of combining human intelligence with computer algorithms
Published in Chapter:
Social Tagging: Properties and Applications
Yong Yu (Shanghai Jiao Tong University, China), Rui Li (Shanghai Jiao Tong University, China), Shenghua Bao (Shanghai Jiao Tong University, China), Ben Fei (IBM China Research Lab, China), and Zhong Su (IBM China Research Lab, China)
Copyright: © 2010
|Pages: 17
DOI: 10.4018/978-1-60566-384-5.ch015
Abstract
Recently, collaborative tagging Web sites such as Del.icio.us and Flickr have achieved great success. This chapter is concerned with the problem of social tagging analysis and mining. More specifically, we discuss five properties of social tagging and their applications: 1) keyword property, which means social annotations serve as human selected keywords for Web resources; 2) semantic property, which indicates semantic relations among tags and Web resources; 3) hierarchical property, which means that hierarchical structure can be derived from the flat social tagging space; 4) quality property, which means that Web resources’ qualities are varied and can be quantified using social tagging; 5) distribution property, which indicates the distribution of frequencies of social tags usually converges to a power-law distribution. These properties are the most principle characteristics, which have been popularly discussed and explored in many applications. As a case study, we show how to improve the social resource browsing by applying the five properties of social tags.