Journal paper published on ACM Transactions on Internet Technology

The increasing popularity of social media platforms like Twitter and Facebook has led to a rise in the presence of hate and aggressive speech on these platforms. Despite the number of approaches recently proposed in the Natural Language Processing research area for detecting these forms of abusive language, the issue of identifying hate speech at scale is still an unsolved problem. In this paper, we propose a robust recurrent neural architecture which has shown to perform in a satisfactory way across different languages, namely English, Italian and German. We address an extensive analysis of the obtained experimental results over the three languages to gain a better understanding of the contribution of the di erent components employed in the system, both from the architecture point of view (i.e., Long Short Term Memory, Gated Recurrent Unit, and bidirectional Long Short Term Memory) and from the feature selection point of view (i.e., social network specific features, emotion lexica, emojis, embeddings). To address such in-depth analysis, we use three freely available datasets for hate speech detection on social media on English, Italian and German.