ProvocationProbe: Instigating Hate Speech Dataset from Twitter (arXiv)
The act of inciting hatred toward a specific group, race, color, gender, religion, or ethnicity is one specific idea within…
Using a multilingual dataset to enhance hateful video detection on YouTube and Bilibili (Singapore University of Technology and Design via Tech Xplore)
MultiHateClip divides videos into three categories: offensive, normal, and hateful, using hate lexicons and human annotations centered on gender-based hatred.…
Educational Security As a Means to Counter Extremism and Hate Speech Among Children (SSRN)
Since children are prime targets for spreading messages of intolerance and extremism, many nations have made educational security a top…
Detecting Hate Speech in Amharic Using Multimodal Analysis of Social Media Memes (ACL Anthology)
Over the course of four months, the researchers gathered 2,000 memes from Facebook, Twitter, and Telegram in order to create…
Audio… Think Change episode 57: is social media’s hate problem beyond repair? (Think Change)
The episode discusses what needs to be done to create digital societies that are safer and more equitable. Visitors examine…
Video… Data Science in the News: Hate Speech (Australian Data Science Network)
“Hate speech” is defined as speech that is harmful in a discriminating manner. In the context of its occurrence, it…
Two Weeks in P/CVE: Free Resources on Countering Extremism, Hate, and Mis-/Disinformation, October 2024 (I/II)
Browse and read from a list of the 170 most popular LinkedIn resources dealing with soft counter-extremism, countering hate speech,…
Multi-task learning model enhances hate speech identification (University of Technology, Sydney via Tech Xplore)
Researchers have created a new multi-task learning (MTL) model, a kind of machine learning model that functions across different datasets,…
A Hate Speech Moderated Chat Application: Use Case for GDPR and DSA Compliance (arXiv)
The foundation for future online platform DSA compliance is laid by the research. A fresh perspective is given on how…
A Target-Aware Analysis of Data Augmentation for Hate Speech Detection (arXiv)
The authors explore the idea of enhancing current data with generative language models, lowering target imbalance, given the unparalleled skills…
Hate Speech Detection Using Cross-Platform Social Media Data In English and German Language (arXiv)
The study focuses on identifying hate speech in two languages in YouTube comments and evaluating how incorporating more data from…
Human and LLM Biases in Hate Speech Annotations: A Socio-Demographic Analysis of Annotators and Targets (arXiv)
There is still much to learn about how the hatred target’s traits interact with the annotator’s. To close this gap,…