期刊名称：Indian Journal of Computer Science and Engineering
印刷版ISSN：2231-3850
电子版ISSN：0976-5166
出版年度：2016
卷号：7
期号：3
页码：75-81
出版社：Engg Journals Publications
摘要：Normally, the messages collected from the social networking applications are highlyunstructured and cluttered that pose a significant level of difficulty for applying conventional miningtechnique. Is such data are not filtered effectively; it will pose a greater deal of difficulty for the user ifs/he wants to generate a customized level of query. This problem can be solved using clustering technique.Hence, we proposed a technique that is capable of visualizing the exact data representation of messagesby applying a unique semantics operation followed by clustering. The study outcome of the technique isfound to have better f1-score and accuracy in comparison to existing system of clustering socialnetworking data.
