• P.Tamilselvan

The most important communication channel in the recent years which is popular among the different social groups is the social media. Millions of tweets are being published on Twitter every day. These tweets reflect the opinions, beliefs and ideas of the publishers which sometimes even affect others. Therefore, it is important to analyze the tweets in order to identify and classify the trends of different users. This helps in providing us valuable information and at the same time it assists to observe what is displayed in order to overcome any unusual events. In this paper, we have introduced a new idea to detect the user affiliation to some anomaly groups by analyzing the short texts extracted from randomly selected Twitter accounts. The primal results are very promising. The next step is to apply this technique to a larger number of accounts and investigate the efficacy and stoutness of the proposed approach.

: Data Mining, Classification, Social Media, Twitter.

"ANALYSIS OF DATA MINING BASED KNN CLASSIFICATION ON TWITTER", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.5, Issue 12, page no.106-116, December-2018, Available :http://www.jetir.org/papers/JETIR1812013.pdf

"ANALYSIS OF DATA MINING BASED KNN CLASSIFICATION ON TWITTER", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.5, Issue 12, page no. pp106-116, December-2018, Available at : http://www.jetir.org/papers/JETIR1812013.pdf