Canhui Li* Pages 29 - 36 ( 8 )
Background: Background: To improve the information efficiency in web text mining, filtration is utilized.Methods:A web content mining technology based on web text mining, augmented information support (AIS), is proposed for improving the web text mining efficiency. Additionally, the AIS technology is applied to the Xiangshan science conference website, and AIS4XSSC text mining system is developed. The developed system is tested for its efficiency, and its main functions are discussed. Results: 192 documents are represented by 8352 vectors, and 192×8352 vectors are obtained; the similarity between 192 vectors is calculated using the cosine of the included angle, 192×192 symmetric matrix is obtained, and 35 categories are formed by hierarchical clustering by using similarity between texts. Conclusion: The results show that the AIS technology can effectively extract information from a large number of web texts. The proposed system improves information retrieval efficiently and can provide valuable information to users.
Web text mining, knowledge discovery, AIS, hall for integrated studies, xiangshan scientific conference, HWMSE.
School of New Media Technology, Hunan Mass Media Vocational and Technical College, Changsha City, Hunan 410100