Twitter Spam Detection Using Naive Bayes Classifier

Twitter is the well liked social media platform that has over 300 million monthly users which post 500 million tweets per day. This is the main reason why spammers use Twitter for their spiteful doings such as spreading malignant software that steals the user personal information and tweets containing fake or faulty URLs, assertively follow or un-follow users and trending fake tweets to get users attention, spread pornography advertisements. In recent years twitter has reportedly collected the data of active users and analyzed their actions, the report clearly shows that over 32 million users have interacted with server for casual information in daily basis. Hence, identifying and filtering the malicious tweets or trends that are harmful or unwanted for users is very important in current social world. This paper discusses about the ways to analyze the tweets and classify them into spam and ham based on the words involved in tweets. Although there are various machine learning and deep learning methods to classify and detect spam tweets like SVM, clustering methods and binary detection models that are used Naive Bayes classifier. Recently, twitter users are experiencing data stealing malware by accessing or visiting unnecessary spam messages or tweets. It has to be considered seriously since many people are losing money or personal information. Besides data stealing malware, fake trends also been a threat. It has to be controlled. Spammers are likely to interact with more people because of the auto-follow option.