Systematic Literature Review on Hate Speech Detection Technology with English and Mixed Language on Social Media Space

Abstract

This comprehensive overview of the literature review assesses the developments in hate speech identification with an emphasis on English-language content, the dynamics of hate and offensive speech detection online has evolved. There is need to analyse and indicate these trends to enable researchers to be able to proffer better solutions, however several researchers also consider datasets with mixed languages but no mixed datasets of Nigerian pidgin English or languages. The PRISMA framework is used in the review, which covers papers from 2018 to 2024, to guarantee methodological rigor. Important discoveries emphasize how difficult it is becoming to identify hate speech because of changing linguistic conventions like code-switching and emoji usage. Machine learning techniques, especially deep learning models such as BERT and LSTM, have demonstrated notable achievements in identifying hate speech. However, there are still difficulties in differentiating hate speech from content that is offensive but not hateful because it is more of semantic and contextual rather lexical. In order to increase model generalizability, the paper also emphasizes the necessity of diverse datasets that include various linguistic subtleties and cultural situations. In the end, even though the accuracy of existing models is excellent, there is always a need for better ways to deal with biases and imbalances in the data. In the future, studies focusing on multilingual and mixed-language datasets should investigate interpretability as a means of improving the efficacy and impartiality of hate speech detection algorithms.