Scientific journal paper Q1
A comprehensive review on automatic hate speech detection in the age of the transformer
Gil Ramos (Ramos, G.); Fernando Batista (Batista, F.); Ricardo Ribeiro (Ribeiro, R.); Pedro Fialho (Fialho, P.); Sérgio Moro (Moro, S.); António Fonseca (Fonseca, A.); Rita Guerra (Guerra, R.); Paula Carvalho (Carvalho, P.); Catarina Marques (Marques, C.); Cláudia Silva (Silva, C.); et al.
Journal Title
Social Network Analysis and Mining
Year (definitive publication)
2024
Language
English
Country
United Kingdom
More Information
Web of Science®

Times Cited: 0

(Last checked: 2024-11-20 20:19)

View record in Web of Science®

Scopus

Times Cited: 0

(Last checked: 2024-11-21 07:25)

View record in Scopus

Google Scholar

Times Cited: 0

(Last checked: 2024-11-19 15:57)

View record in Google Scholar

Abstract
The rapid proliferation of hate speech on social media poses significant challenges to maintaining a safe and inclusive digital environment. This paper presents a comprehensive review of automatic hate speech detection methods, with a particular focus on the evolution of approaches from traditional machine learning and deep learning models to the more advanced Transformer-based architectures. We systematically analyze over 100 studies, comparing the effectiveness, computational requirements, and applicability of various techniques, including Support Vector Machines, Long Short-Term Memory networks, Convolutional Neural Networks, and Transformer models like BERT and its multilingual variants. The review also explores the datasets, languages, and sources used for hate speech detection, noting the predominance of English-focused research while highlighting emerging efforts in low-resource languages and cross-lingual detection using multilingual Transformers. Additionally, we discuss the role of generative and multi-task learning models as promising avenues for future development. While Transformer-based models consistently achieve state-of-the-art performance, this review underscores the trade-offs between performance and computational cost, emphasizing the need for context-specific solutions. Key challenges such as algorithmic bias, data scarcity, and the need for more standardized benchmarks are also identified. This review provides crucial insights for advancing the field of hate speech detection and shaping future research directions.
Acknowledgements
--
Keywords
Hate speech detection,Machine learning,Deep learning,Transfer learning,Transformers,Literature review
  • Computer and Information Sciences - Natural Sciences
  • Civil Engineering - Engineering and Technology
  • Media and Communications - Social Sciences
Funding Records
Funding Reference Funding Entity
CERV-2021-EQUAL (101049306) Comissão Europeia