Evaluating Simple Debiasing Techniques in RoBERTa-based Hate Speech Detection Models (arXiv)
The annotation bias in the underlying hate speech datasets used to train these models is known to cause bias against…
Echoes of Discord: Forecasting Hater Reactions to Counterspeech (arXiv)
Hate speech propagates negativity and divisiveness online, undermining inclusivity. It is acknowledged that counterspeech can help lessen these negative effects.…
Unveiling Hate Speech Dynamics: An Examination of Discourse Targeting the Spanish Meteorological Agency (AEMET) (Social Inclusion)
This article examines hate speech on the social media platform X directed at the Spanish meteorological governmental organization, AEMET. We…
Ensuring safety in digital spaces: Detecting code-mixed hate speech in social media posts (Data & Knowledge Engineering)
With a performance of 75% accuracy, the results show that the transliteration strategy outperforms both raw and translated data by…
The Dialects Gap: A Multi-Task Learning Approach for Enhancing Hate Speech Detection in Arabic Dialects (SSRN)
The suggested approach uses shared representation knowledge across five Arabic dialects—Egyptian, Saudi, Levant, Gulf, and Algerian—and is intended to detect…
A survey of textual cyber abuse detection using cutting-edge language models and large language models (arXiv)
The study offers a thorough examination of the many types of abuse that are common on social media, with an…
Two Weeks in Soft Security: Free Resources on Countering Extremism, Hate, and Disinformation, January 2025 (I/II)
Browse and read from a list of the 165 most popular LinkedIn resources dealing with soft counter-extremism, countering hate speech,…
The Challenges of Creating a Parallel Multilingual Hate Speech Corpus: An Exploration (ACL Anthology)
In order to investigate the prospect of employing machine translation to create a parallel multilingual hate speech dataset, the researchers…
SAFE-MEME: Structured Reasoning Framework for Robust Hate Speech Detection in Memes (arXiv)
Two multimodal hate speech datasets, MHS and MHS-Con, which record fine-grained hostile abstractions in everyday and confusing situations, are curated…
Two Weeks in Soft Security: Free Resources on Countering Extremism, Hate, and Disinformation, December 2024 (II/II)
Browse and read from a list of the 148 most popular LinkedIn resources dealing with soft counter-extremism, countering hate speech,…
Recent Advances in Online Hate Speech Moderation: Multimodality and the Role of Large Models (ACL Anthology)
The multimodal character of digital information makes it even more difficult to moderate hate speech (HS) in the dynamic online…
The Content Moderator’s Dilemma: Removal of Toxic Content and Distortions to Online Discourse (arXiv)
The authors use text embeddings from computational linguistics to develop and evaluate a approach for quantifying the distortions caused by…