A deep learning model for Twitter spam detection

Md. Zulfikar Alom, Barbara Carminati, Elena Ferrari

Abstract: Social networking platforms have become a popular way for Internet surfers to meet and interact. Twitter is one of the most popular social networking platforms where users can read the news, share ideas, discuss social issues, as well as stay in touch with friends and families. Due to its huge popularity, it has also become a target for spammers. Until now, researchers have developed many machine learning (ML) based methods for detecting spammers on Twitter. However, the available ML-based methods cannot efficiently detect spammers on Twitter due to possible data manipulations by spam users to avoid detection mechanisms. As an alternative to ML-based detection, in this paper, we present a new approach based on deep learning (DL) techniques. Our approach leverages both on tweet text as well as users’ meta-data (e.g., age of an account, number of followings/followers, and so on) to detect spammers. We compare the performance of the proposed approach with five ML-based and two DL-based state of the art approaches on two different real-world datasets, showing a gain in performance when using our approach.