This repo complements AAAI student paper by the name, "Mind Your Language: Abuse and Offense Detection for Code-Switched Languages" It contains the following files:
- Model used in the paper
- Embedding Matrix for the embeddings trained
- Dataset - HEOT
- Hinglish Profanity List created by us
- Dictionary for translation of Hinglish words
- Results that we got after running the model
- Some samples of the tweets on which we ran the model
If you use this repo or any part of it, please cite our paper as: @misc{kapoor2018mind, title={Mind Your Language: Abuse and Offense Detection for Code-Switched Languages}, author={Raghav Kapoor and Yaman Kumar and Kshitij Rajput and Rajiv Ratn Shah and Ponnurangam Kumaraguru and Roger Zimmermann}, year={2018}, eprint={1809.08652}, archivePrefix={arXiv}, primaryClass={cs.CL} }