• M.Mohan prrasad
• Maria Savari Antony James
• K.Paneerselvam
• R.Naveen Kumar
• Dr.N.Revathy

In Online Social Network like facebook, twitter has been exposed to more fake account for normal peoples and especially for celebrities. These activities lead to more cyber crime and memory management issues. In order to prevent these kinds of attack, new mechanism has to be proposed to prevent the legitimate user from the malicious user. In this paper, a novel mechanism named as Trust Computation using unsupervised learning model. Fundamental process of this application is to generate reputation of the account through trust computation. The trust computation is enabled with verifier through multiple voting and rating technique on several characteristics such as validating the email address of the user, mobile phone number, schooling details and employment details with friend list and mutual friends in the group. The model effectively isolates fake follower accounts from genuine users. The experimental results prove that proposed system outperforms the existing approaches in terms of accuracy and efficiency parameters.

Fake user Detection, Unsupervised Learning.

"A study of detecting the fake users by using unsupervised learning algorithm", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.5, Issue 11, page no.191-192, November-2018, Available :http://www.jetir.org/papers/JETIR1811426.pdf

"A study of detecting the fake users by using unsupervised learning algorithm", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.5, Issue 11, page no. pp191-192, November-2018, Available at : http://www.jetir.org/papers/JETIR1811426.pdf