Hate is in the air! But where? Introducing an algorithm to detect hate speech in digital microenvironments

Abstract

With the objective of facilitating and reducing analysis tasks undergone by law enforcement agencies and service providers, and using a sample of digital messages (i.e., tweets) sent via Twitter following the June 2017 London Bridge terror attack (N = 200,880), the present study introduces a new algorithm designed to detect hate speech messages in cyberspace. Unlike traditional designs based on semantic and syntactic approaches, the algorithm hereby implemented feeds solely on metadata, achieving high level of precision. Through the application of the machine learning classification technique Random Forests, our analysis indicates that metadata associated with the interaction and structure of tweets are especially relevant to identify the content they contain. However, metadata of Twitter accounts are less useful in the classification process. Collectively, findings from the current study allow us to demonstrate how digital microenvironment patterns defined by metadata can be used to create a computer algorithm capable of detecting online hate speech. The application of the algorithm and the direction of future research in this area are discussed.

A Systematic Literature Review of Different Machine Learning Methods on Hate Speech Detection

“…Paper [24] approached a method for hate speech detection in digital microenvironments. The combination of the people (i.e., accounts), who say things (i.e., tweets) to other people (i.e., other accounts), is the definition of digital microenvironments in cyberspace.…”

“…But where? Introducing an algorithm to detect hate speech in digital microenvironments[24] Springer Link 2020 Developing an online hate classifier for multiple social media platforms…”

Crime and fear in public places

“…The interplay between the police practice and research seems central to create evidence-based strategies needed to move away from unsafety and violence surrounding the ODS. Esteve, Miró-Linares & Rabasa, 2018;Miró-Llinares, Moneva, & Esteve, 2018). In general terms, Big data allows us to collect data as they are generated and compared over time (Bello-Orgaz, Jung, & Camacho, 2016;McAfee, Brynjolfsson, Davenport, Patil & Barton, 2012).…”

dictNN: A Dictionary-Enhanced CNN Approach for Classifying Hate Speech on Twitter

“…Most current approaches include user data and other metadata in the analysis in order to improve the models' accuracy (Mathew et al, 2019;Ribeiro et al, 2018;Waseem and Hovy, 2016;Miró-Llinares et al, 2018;Stoop et al, 2019). However, the focus of these models lies on identifying hateful user accounts and environments, rather than hateful content per se.…”