A Survey of Internet Data Mining Technologies Based on Machine Learning
Lin Du, Yehong Han · Advances in engineering research/Advances in Engineering Research · 2015
As a knowledge discovery in internet, data mining technology is the cross of machine learning and databases technology.Data mining can provide massive amounts of data analysis using machine learning techniques and manage massive amounts of data by the use of database technology.The goal of machine learning is to simulate and realize human learning behavior in order to optimize a performance criterion using past experience and example data.Two kinds of internet data mining technologies which include rank learning and topic model learning are introduced in this paper.As a supervised learning sorting method, the task of rank learning is sorting the retrieved pages for a given query.As a Bayesian model, topic model learning is designed to automatically extract all possible topics and each topic page from the index page, so that the web page and query statement can match on the topic.The latest researches about above areas are reviewed.