Offensive Text Detection using NLP

This project aims to detect offensive ( Racist , Sexist etc ) text from social media posts (tweets) using NLP techniques and sentiment analysis with the help of Machine Learning / Deep learning models.

Please find the Experience paper: Experience Paper

References

Mahmud, A., Ahmed, K.Z. and Khan, M., 2008. Detecting flames and insults in text. https://www.researchgate.net/publication/49242911_Detecting_flames_and_insults_in_text

Kshirsagar, R., Cukuvac, T., McKeown, K. and McGregor, S., 2018. Predictive embeddings for hate speech detection on twitter. arXiv preprint arXiv:1809.10644. https://aclweb.org/anthology/W18-5104

Amplayo, R.K. and Occidental, J., 2015. Multi-level classifier for the detection of insults in social media. In Proceedings of 15th Philippine Computing Science Congress. https://www.researchgate.net/publication/273381302_Multi-level_classifier_for_the_detection_of_insults_in_social_media

Malmasi, S. and Zampieri, M., 2017. Detecting hate speech in social media. arXiv preprint arXiv:1712.06427. https://arxiv.org/abs/1712.06427

Sax, S., 2016. Flame wars: Automatic insult detection. https://cs224d.stanford.edu/reports/Sax.pdf

Biere, S., Bhulai, S. and Analytics, M.B., 2018. Hate speech detection using natural language processing techniques. Master Business AnalyticsDepartment of Mathematics Faculty of Science. https://beta.vu.nl/nl/Images/werkstuk-biere_tcm235-893877.pdf

Çano, E. and Morisio, M., 2019. Word embeddings for sentiment analysis: a comprehensive empirical survey. arXiv preprint arXiv:1902.00753. https://www.academia.edu/38464940/Word_Embeddings_for_Sentiment_Analysis_A_Comprehensive_Empirical_Survey