A survey on automatic detection of hate speech in text. Paula Fortuna and Sérgio Nunes. 2018. ACM Comput. Surv. 51, 4, Article 85 (July 2018), 30 pages. https://doi.org/10.1145/3232676 This survey provides a structured overview of previous approaches to automatic hate speech detection in text, including core algorithms, methods, and main features. It discusses the complexity of the concept of hate speech, which is defined in many platforms and contexts, and provides a unifying definition. The area has significant potential for societal impact, particularly in online communities and digital media platforms. The development and systematization of shared resources, such as guidelines, annotated datasets in multiple languages, and algorithms, is crucial for advancing automatic hate speech detection. The survey analyzes previous research in the field, discusses motivations for studying hate speech automatic detection, and presents theoretical aspects of the topic. It distinguishes different definitions of hate speech, analyzes particular cases, relates hate speech to other close concepts, and examines how hate speech online has evolved. A systematic literature review is conducted, with detailed methods and results, including quantitative and qualitative data. The survey also presents related datasets and open-source projects, summarizes main challenges in the field, and highlights research opportunities. The survey defines hate speech as language that attacks or diminishes, incites violence or hate against groups based on specific characteristics, and can occur in subtle forms or when humor is used. It also discusses particular cases and examples of hate speech, such as Facebook's rules for hate speech detection. The survey compares hate speech with other related concepts, such as cyberbullying, abusive language, discrimination, and extremism. The survey presents a systematic literature review of research on automatic hate speech detection, including the number of publications, publication venues, keywords, and algorithms used. It discusses the challenges and opportunities in the field, and highlights the importance of developing models that can detect subtle forms of discrimination and hate speech. The survey concludes with a summary of the main contributions and future perspectives in the field of automatic hate speech detection.A survey on automatic detection of hate speech in text. Paula Fortuna and Sérgio Nunes. 2018. ACM Comput. Surv. 51, 4, Article 85 (July 2018), 30 pages. https://doi.org/10.1145/3232676 This survey provides a structured overview of previous approaches to automatic hate speech detection in text, including core algorithms, methods, and main features. It discusses the complexity of the concept of hate speech, which is defined in many platforms and contexts, and provides a unifying definition. The area has significant potential for societal impact, particularly in online communities and digital media platforms. The development and systematization of shared resources, such as guidelines, annotated datasets in multiple languages, and algorithms, is crucial for advancing automatic hate speech detection. The survey analyzes previous research in the field, discusses motivations for studying hate speech automatic detection, and presents theoretical aspects of the topic. It distinguishes different definitions of hate speech, analyzes particular cases, relates hate speech to other close concepts, and examines how hate speech online has evolved. A systematic literature review is conducted, with detailed methods and results, including quantitative and qualitative data. The survey also presents related datasets and open-source projects, summarizes main challenges in the field, and highlights research opportunities. The survey defines hate speech as language that attacks or diminishes, incites violence or hate against groups based on specific characteristics, and can occur in subtle forms or when humor is used. It also discusses particular cases and examples of hate speech, such as Facebook's rules for hate speech detection. The survey compares hate speech with other related concepts, such as cyberbullying, abusive language, discrimination, and extremism. The survey presents a systematic literature review of research on automatic hate speech detection, including the number of publications, publication venues, keywords, and algorithms used. It discusses the challenges and opportunities in the field, and highlights the importance of developing models that can detect subtle forms of discrimination and hate speech. The survey concludes with a summary of the main contributions and future perspectives in the field of automatic hate speech detection.