Papers › Enhancing social network hate detection using back translation and GPT-3 augmentations...
Enhancing social network hate detection using back translation and GPT-3 augmentations during training and test-time
Seffi Cohen, Dan Presil, Or Katz, Ofir Arbili, Shvat Messica, Lior Rokach
Social media platforms have become an essential means of communication, but they also serve as a breeding ground for hateful content. Detecting hate speech accurately is challenging due to factors such as slang and implicit hate speech. In response to these challenges, this paper presents a novel ensemble approach utilizing DeBERTa models, integrating back-translation and GPT-3 augmentation techniques during both training and test time. This method aims to address the complexities associated with detecting hate speech, resulting in more robust and accurate results. Our findings indicate that the proposed approach significantly enhances hate speech detection performance across various metrics and models in both the Parler and GAB datasets. For reproducibility and further exploration, our code is publicly available at https://github.com/OrKatz7/parler-hate-speech.
Code
Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Results from the paper archive 2025-07-28
No leaderboard rows for this paper in the archive.
Methods
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections