Spam Tweets Detection Based On Machine Learning Approach
R Phad Kanchan, B Bhosale Supriya, A Salke Bhagyshri · International journal of advance research and innovative ideas in education · 2018
Online social networking is very vast growing growth today’s world but attacks on it is more common, Amongst them one of the attack is twitter attack in this Spammers spread various malicious tweets which may have form like as links or hash tags on the website and online services , which are too harmful to real users. In order to prevent this attacks training tweets are added and further this issues is addressed by extracting 12 lightweight features such as account age, no of followers, no of following, no of tweets, no of re-tweets etc. For streaming tweet spam detection a feature discretization is important to spam detection performance. In system there is a big ground- truth which includes total 600 public tweets based on the URL based security tool. Spam detection mainly builds the classification model which includes the binary classification and further it can be solved by the machine learning based algorithm. The machine learning algorithms such as Naive Bayesian classifier or support vector machine classifier reported the behavior of models. System reported the impact of the data related factors, such as spam to non-spam ratio, training data size, and data sampling, to the detection performance. The feature of implemented system is simple and time varying spam tweet detection. The System is shows as the spam detection is big challenge and it bridge the gap between the performance evaluation and mainly focus on the data, feature and model to identify the genuine user and report the spam user by giving the answer in binary value.