Open AccessIdentification of Fake vs. Real Identities on Social Media using Random Forest and Deep Convolutional Neural Network
Author(s) -
Bharat S. Borkar,
Rajesh Purohit
Publication year - 2019
Publication title -
international journal of engineering and advanced technology
Language(s) - English
Resource type - Journals
ISSN - 2249-8958
DOI - 10.35940/ijeat.a9739.109119
Subject(s) - identification (biology) , identity (music) , social media , preprocessor , computer science , convolutional neural network , fake news , artificial intelligence , random forest , social network (sociolinguistics) , identity theft , internet privacy , social identity theory , machine learning , data science , computer security , world wide web , psychology , social group , social psychology , physics , botany , acoustics , biology
Identity detection is very essential in social media platforms, various platform has facing fake accounts influence since couple of years in current eras. Many researchers has introduces approach for identify the fake profiles, but still system cant able to solve such issues. As these fake identities are being used by offenders for various malicious purposes, it has become necessity of time to identify them. The fake identities are categorized into two main types’ i.e. fake identities by bots and fake identities by humans. This system removes fake identities by bots during preprocessing and focuses mainly on identification of fake identities by humans as very little research has been made till now on the fake identities by humans. For classification we test for two different algorithms i.e. Random Forest (RF) and Recurrent Neural Network (RNN). The classification is based on various features such as user name, location, friends count, followers count and so on. Here, dataset used is that of Twitter.