ZANG words and similarities calculationin 2013. The

ZANG Xiayon, WANG Ting discovered journal in 20091defines Topic detection and Tracking and main idea behindthis paper to collect and organize the scattered information.Chenjing Han2 explains the hotspot discovery based on,density clustering of features words and similarities calculationin 2013. The main idea behind this paper is as per the lattersinput and plays a key role in the discovery of the letter.Cooley B R W. Web usage mining explains in 2010.The mainidea behind this paper to find useful information from themassive web page information according to the task of webmining. XIAO Yi, ZHANG Lin, NIE Xiao-Yi. design andimplement in 2013.The main idea behind this paper how todesign and implement web crawling based on web mining.YAO Quanzhu, SONG Zhili, PENG Cheng. researched On textcategorization based on LDA in 2011.The main Idea behindthis paper Simple splicing segmented words would introducea large number of insignificant strings, in order to obtain acompendious candidate string, the Splicing algorithm requiresstrong support from filtering function, and we adopted a multilevelfiltering strategy. WANG Wei, YANG Wu,QI Haifeng. In2009 published general on Network Hotspot Topic DetectionAlgorithm based on Multicenter Model. The main idea behindthis paper is a counting the actual news reporting data, whichindicate the central level the of the report according to theirappearance order. For the circumstance that the multicenter isbuilt on the initial center only when relevant attributes (suchas time, place and the characters) of the initial center change,other centers would be established. If the main attribute ofthe event does not change, the event can still be consideredto remain in the initial center position. Hengmin Zhu, WeiweiZhu. Study on Web Topic Online Clustering Approach Basedon Single-Pass Algorithm in 2011. The main idea behind thisresearched is to carry On topic text clustering. Xiaoqing Ding.Research and Implementation of Hottopic discovery on Microblog in 2014.The main idea behind this paper is Web miningbasedWeibo hot topic discovery algorithm is to excavate anddiscover the most popular topic from the massive data. Chen F,Farahat A, Brants T. in 2004 researched on Similarity measuresand source pair information in story link detection. The mainidea behind this researched is in Web mining how to evaluatethe similarity between two vectors.