Design and Development of Artificial Neural Networks to Identify Fake Profiles

Abstract

In this present generation, the social life of everyone has become associated with the online social networks. Making friends and keeping in contact with them and their updates has become easier. But with the rapid growth of these social networking sites, many problems like fake profiles, online impersonation have also grown. An algorithm was used in which the profiles are ranked according to the number of interactions, tags, wall posts, and friends over time. Profiles that have a high rank are considered to be real while profiles having a low rank are considered to be fake. Unfortunately, this technique was found to be unreliable because it failed to take into account the possibility that real profiles can be ranked low and fake profiles can be ranked high. In this project, we use an artificial neural network to determine what are the chances that a friend request is authentic or not. It intends to focus on the dangers of a bot in the form of a fake profile on your social media. This solution would come in the form of an algorithm. The algorithm would be able to determine if a current friend request that a user gets online is an actual person or if it is a bot or if it is a fake friend request fishing for information. We need a training dataset to train our model and later verify if the profiles are fake or not. Through the use of different libraries, we can easily design and develop an artificial neural network. The language we choose to use is Python. We also consider the parameters of the social networking page which are the most important to our solution. For training set, the features that we use determine a fake profile are Account age, Gender, User age, Number of messages sent out, Number of friend requests sent out. This proposed solution will help in determining whether the profile is genuine or not and gives us an accuracy of 96%.