Spam Detection and Spammer Community Detection in Social Media Platform Using Machine Learning Techniques

Abstract

In recent years, social media platforms have experienced a surge in popularity, leading to an increase in spam and spammer communities. This paper presents a comprehensive study on spam detection and spammer community detection in social media platforms using machine learning techniques. The proposed approach focuses on three main features: Review-Behavioral (RB) Based features, Review-Linguistic (RL) Based Features, and User-Behavioral (UB) Based Features. By combining these features, we aim to create a robust and accurate spam detection model that effectively identifies spam content and spammer communities in social media networks. The Review-Behavioral (RB) Based features focus on the patterns and tendencies observed in user-generated content, such as the frequency of posting, the time between posts, and the distribution of ratings. Review-Linguistic (RL) Based Features, on the other hand, analyze the linguistic characteristics of the content, including the use of specific keywords, the complexity of the text, and sentiment analysis. Lastly, User-Behavioral (UB) Based Features examine the behavior of users in the social media platform, including their social connections, interactions, and activity patterns. By incorporating these features into a machine learning model, we aim to develop an effective spam detection and spammer community detection system that can be used to protect social media platforms from malicious activities. The results of this study will provide valuable insights into the effectiveness of these features in identifying spam and spammer communities, as well as contribute to the ongoing efforts to improve the security and integrity of social media networks.