Graphically Speaking: Unmasking Abuse in Social Media with Conversation Insights (arXiv)
It can be difficult to discern abusive language in social media interactions because it frequently depends on the conversational context,…
Assessing Transformers and Traditional Models for Spanish-English Code-Switched Hate Detection (Tech Rxiv)
Research on hate speech identification has mostly examined monolingual situations; multilingual and code-switched languages, which provide unique linguistic complications, have…
Two Weeks in Soft Security: Free Resources on Countering Extremism, Hate, and Disinformation, March 2025 (II/II)
Browse and read from a list of the 190 most popular LinkedIn resources, including 3 audios and 18 videos, dealing…
A Literature Review of Textual Hate Speech Detection Methods and Datasets (MDPI)
Toxic online discourses have the potential to cause disputes or damage communities. Without a formal study of hate speech datasets,…
Enhancing cross-lingual hate speech detection through contrastive and adversarial learning (Engineering Applications of Artificial Intelligence)
The proposed method adapts characteristics from well-resourced languages to effectively detect hate speech in low-resource environments, addressing the lack of…
Can LLM guardrails prevent harassment or hate speech? (milvus)
Although they can lessen it, large language model (LLM) guardrails cannot absolutely stop hate speech or harassment. Guardrails are rules…
Human-in-the-Loop Hate Speech Classification in a Multilingual Context (ACL Anthology)
Online hate speech has increased in tandem with the movement of public discourse online. Although a number of promising methods…
Two Weeks in Soft Security: Free Resources on Countering Extremism, Hate, and Disinformation, March 2025 (I/II)
Browse and read from a list of the 230 most popular LinkedIn resources, including 9 audios and 17 videos, dealing…
Two Weeks in Soft Security: Free Resources on Countering Extremism, Hate, and Disinformation, February 2025 (II/II)
Browse and read from a list of the 245 most popular LinkedIn resources, including 16 audios and 7 videos, dealing…
Multilingual and Multi-Aspect Hate Speech Analysis (SSRN)
The majority of current hate speech analysis research focuses on single-task categorization and monolingual datasets. The scholars present a new…
Evaluation of Hate Speech Detection Using Large Language Models and Geographical Contextualization (arXiv)
The study looks at how well LLMs do in identifying hate speech in a variety of geographical locations and multilingual…
Generate, Prune, Select: A Pipeline for Counterspeech Generation against Online Hate Speech (arXiv)
Natural Language Generation (NLG) has the unique ability to create scalable solutions to address the growing problem of hate speech…