This repository contains the proposed work on HOLD-Z from DravidianLangtech-2024@EACL HOLD-Z:
HOLD-Z: Hate and Offensive Language Detection in Telugu Codemixed Text
If you find this repo helpful, please cite the following paper: https://aclanthology.org/2024.dravidianlangtech-1.22/
Hateful online content is a growing concern, es- pecially for young people. While social media platforms aim to connect us, they can also be- come breeding grounds for negativity and harm- ful language. This study tackles this issue by proposing a novel framework called HOLD-Z, specifically designed to detect hate and offen- sive comments in Telugu-English code-mixed social media content. HOLD-Z leverages a combination of approaches, including three powerful models: LSTM architecture, Zypher, and openchat_3.5. The study highlights the effectiveness of prompt engineering and Quan- tized Low-Rank Adaptation (QLoRA) in boost- ing performance.
