4chan & 8chan embeddings

We have collected over 30M messages from the publicly available /pol/ message boards on 4chan and 8chan, and compiled them into a model of toxic language use. The trained word embeddings (0.4GB) are released for free and may be useful for further study on toxic discourse or to boost hate speech detection systems: this https URL.

Incidents & harms Language & NLP cs.CL Hate Speech and Cyberbullying Detection

Paper

References (12)

01Right-wing German Hate Speech on Twitter: Analysis and Automatic DetectionS. Jaki, T. Smedt2019 · arXiv.org · 69 citations In Library

02“The system is rigged against me:” exploring a white supremacist community on 4Chan and perceptions of white supremacy at the University of PittsburghA.A. Shultz2019 · 1 citation

03Post-Truth Protest: How 4chan Cooked Up the Pizzagate BullshitM. Tuters, Emilija Jokubauskaitė, D. Bach2018 · M/C Journal · 44 citations

04The mainstreaming of far-right extremism online and how to counter it : A case study on UK, US and French electionsJacob Davey, E. Saltman, J. Birdwell2018 · 10 citations

05Media Manipulation and Disinformation OnlineB. Lewis, Alice E. Marwick2017 · 813 citations

06Online misogyny and feminist digilantismE. Jane2016 · 198 citations

07A Conspiracy of Fishes, or, How We Learned to Stop Worrying About #GamerGate and Embrace Hegemonic MasculinityS. Chess, A. Shaw2015 · 394 citations

08Distributed Representations of Words and Phrases and their CompositionalityTomas Mikolov, I. Sutskever, Kai Chen et al.2013 · Neural Information Processing Systems · 35k citations In Library

09Gensim -- Statistical Semantics in PythonRadim Rehurek, Petr Sojka2011 · 251 citations

10Online Misogyny, Harassment and Hate CrimesA. Powell, N. Henry2017 · 13 citations

11Trolls, hackers, anons: Conspiracy theories in the peripheries of the webMattia Thibault2016 · 14 citations

12Trumping the mainstream: The conquest of democratic politics by the populist radical right2018

Similar papers

Measuring Online Hate on 4chan using Pre-trained Deep Learning ModelsAdrian Bermudez-Villalva, M. Mehrnezhad, Ehsan Toreini2025 · IEEE Transactions on Technology and Society · 7 citations In Library

Measuring Online Hate on 4chan Using Pre-Trained Deep Learning ModelsAdrian Bermudez-Villalva, Maryam Mehrnezhad, Ehsan Toreini2025 · IEEE Transactions on Technology and Society In Library

Raiders of the Lost Kek: 3.5 Years of Augmented 4chan Posts from the Politically Incorrect BoardAntonis Papasavva, Savvas Zannettou, Emiliano De Cristofaro et al.2020 · OpenBU (Boston University) In Library

Raiders of the Lost Kek: 3.5 Years of Augmented 4chan Posts from the Politically Incorrect BoardAntonis Papasavva, Savvas Zannettou, Emiliano De Cristofaro et al.2020 · arXiv (Cornell University) In Library

Raiders of the Lost Kek: 3.5 Years of Augmented 4chan Posts from the Politically Incorrect BoardAntonis Papasavva, Savvas Zannettou, Emiliano De Cristofaro et al.2020 · Proceedings of the International AAAI Conference on Web and Social Media In Library

Kek, Cucks, and God Emperor Trump: A Measurement Study of 4chan’s Politically Incorrect Forum and Its Effects on the WebGabriel Emile Hine, Jeremiah Onaolapo, Emiliano De Cristofaro et al.2017 · Proceedings of the International AAAI Conference on Web and Social Media In Library

Kek, Cucks, And God Emperor Trump: A Measurement Study Of 4Chan'S Politically Incorrect Forum And Its Effects On The WebGabriel Emile Hine, Jeremiah Onaolapo, Emiliano De Cristofaro et al.2017 · Zenodo (CERN European Organization for Nuclear Research) In Library

Toxicity in Texts and Images on the InternetDenis Gordeev, В.В. Потапов2020 · Lecture notes in computer science In Library

A Machine Learning Approach to Identify Toxic Language in the Online SpaceLisa Kaati, Amendra Shrestha, Nazar Akrami2022 · International Conference on Advances in Social Networks Analysis and Mining · 6 citations In Library

Abusive Language Detection Using BERT Pre-trained EmbeddingNasrin Baratalipour, Ching Y. Suen, Olga Ormandjieva2020 · Lecture notes in computer science · 1 citation In Library

Source of record

arXiv

44B

Welcome.

This panel sticks with you. Pick anything below and it opens right beside it, so you can dig through 60,000-plus records without ever losing your spot here.

Travel 44B

LibraryPapers, policy, standards, statute LabsEvery organization building AI ModelsIntelligence, price, and speed BenchmarksThe evaluation catalog IncidentsAI failures and harms SearchOne field across everything DashboardThe state of AI accountability in NY 44B RegistryThe Art. 44-B compliance portal