A Unified Deep Learning Architecture for Abuse Detection

Hate speech, offensive language, sexism, racism and other types of abusive behavior have become a common phenomenon in many online social media platforms. In recent years, such diverse abusive behaviors have been manifesting with increased frequency and levels of intensity. This is due to the openness and willingness of popular media platforms, such as Twitter and Facebook, to host content of sensitive or controversial topics. However, these platforms have not adequately addressed the problem of online abusive behavior, and their responsiveness to the effective detection and blocking of such inappropriate behavior remains limited. In fact, up to now, they have entered an arms race with the perpetrators, who constantly change tactics to evade the detection algorithms deployed by these platforms. Such algorithms are typically custom-designed and tuned to detect only one specific type of abusive behavior, but usually miss other related behaviors. In the present paper, we study this complex problem by following a more holistic approach, which considers the various aspects of abusive behavior. To make the approach tangible, we focus on Twitter data and analyze user and textual properties from different angles of abusive posting behavior. We propose a deep learning architecture, which utilizes a wide variety of available metadata, and combines it with automatically-extracted hidden patterns within the text of the tweets, to detect multiple abusive behavioral norms which are highly inter-related. We apply this unified architecture in a seamless, transparent fashion to detect different types of abusive behavior (hate speech, sexism vs. racism, bullying, sarcasm, etc.) without the need for any tuning of the model architecture for each task. We test the proposed approach with multiple datasets addressing different and multiple abusive behaviors on Twitter. Our results demonstrate that it largely outperforms the state-of-art methods (between 21 and 45% improvement in AUC, depending on the dataset).