【文件属性】:
文件名称:【Web挖掘】PageRank and Interaction Information Retrieval
文件大小:103KB
文件格式:PDF
更新时间:2018-05-28 02:58:07
pagerank web挖掘
Web挖掘相关文档
The PageRank method is used by the Google Web
search engine to compute the importance of Web pages.
Two different views have been developed for the interpretation
of the PageRank method and values: (a) stochastic
(random surfer): the PageRank values can be
conceived as the steady-state distribution of a Markov
chain, and (b) algebraic: the PageRank values form the
eigenvector corresponding to eigenvalue 1 of the Web
link matrix. The Interaction Information Retrieval (I2R)
method is a nonclassical information retrieval paradigm,
which represents a connectionist approach based on dynamic
systems. In the present paper, a different interpretation
of PageRank is proposed, namely, a dynamic systems
viewpoint, by showing that the PageRank method
can be formally interpreted as a particular case of the Interaction
Information Retrieval method; and thus, the
PageRank values may be interpreted as neutral equilibrium
points of the Web.