Spammer Group Detection Using Machine Learning Technology for Observation of New Spammer Behavioral Features

Recently, the rapid growth in number of customer reviews on e-commence platforms and amount user-generated content has begun to have a profound impact purchasing decisions. To counter negative social media marketing, some firms hiring people generate fake which either promote their own products or damage competitor's reputation. This study proposes framework, takes advantage both supervised unsupervised learning techniques, for observation behaviors among spammers. Then, based behavior participants web forums, authors build up post-reply network. The main focus is behavior-related features reviews, propagation, popularity. primary objective this an effective online spammer detection model method detailed work can be used improve performance models. An experiment carried out with real dataset, results indicate that these new are important identifying Finally, random walk clustering applied investigate Some interesting observed interactions between group spammers could subjected further research.