We evaluate the viability of multilingual learning for the task of hate speech detection. We also experiment with adversarial learning as a means of creating a multilingual model. Ultimately our multilingual models have had worse results than their monolignual counterparts. We find that the choice of word representations (word embeddings) is very crucial for deep learning as a simple switch between MUSE and ELMo embeddings has shown a 3-4% increase in accuracy. This also shows the importance of context when dealing with online content.

Hate speech should be tackled and prosecuted based on how it is operationalized. However, the existing theoretical definitions of hate speech are not sufficiently fleshed out or easily operable. To overcome this inadequacy, and with the help of interdisciplinary experts, we propose an empirical definition of hate speech by providing a list of 10 hate speech indicators and the rationale behind them (the indicators refer to specific, observable, and measurable characteristics that offer a practical definition of hate speech). A preliminary exploratory examination of the structure of hate speech, with the focus on comments related to migrants (one of the most reported grounds of hate speech), revealed that two indicators in particular, denial of human rights and promoting violent behavior, occupy a central role in the network of indicators. Furthermore, we discuss the practical implications of the proposed hate speech indicators—especially (semi-)automatic detection using the latest natural language processing (NLP) and machine learning (ML) methods. Having a set of quantifiable indicators could benefit researchers, human right activists, educators, analysts, and regulators by providing them with a pragmatic approach to hate speech assessment and detection.

From a computer science perspective, addressing on-line hate speech is a challenging task that is attracting the attention of both industry (mainly social media platform owners) and academia. In this chapter, we provide an overview of stateof-the-art data-science approacheshow they define hate speech, which tasks they solve to mitigate the phenomenon, and how they address these tasks. We limit our investigation mostly to (semi-)automatic detection of hate speech, which is the task that the majority of existing computer science works focus on. Finally, we summarize the challenges and the open problems in the current data-science research and the future directions in this field. Our aim is to prepare an easily understandable report, capable to promote the multidisciplinary character of hate speech research. Researchers from other domains (e.g., psychology and sociology) can thus take advantage of the knowledge achieved in the computer science domain but also contribute back and help improve how computer science is addressing that urgent and socially relevant issue which is the prevalence of hate speech in social media.

No abstract

Growing amount of comments make online discussions difficult to moderate by human moderators only. Antisocial behavior is a common occurrence that often discourages other users from participating in discussion. We propose a neural network based method that partially automates the moderation process. It consists of two steps. First, we detect inappropriate comments for moderators to see. Second, we highlight inappropriate parts within these comments to make the moderation faster. We evaluated our method on data from a major Slovak news discussion platform.