yangzilong1986 / hate_speech_detection-nlp

Created Hate speech detection model using Count Vectorizer & XGBoost Classifier with an Accuracy upto 0.9471, which can be used to predict tweets which are hate or non-hate.

Hate_Speech_Detection_NLP

This is Hate speech detection model created using Count Vectorizer and XGBoost Classifier with an Accuracy upto 0.9471, train-test split of 70:30, which can be used to predict whether tweets are hate or non-hate.

---

Dataset:

• Dataset using Twitter data, isused to research hate-speech detection. The text is classified as: hate-speech, offensive language, and neither. Due to the nature of the study, it’s important to note that this dataset contains text that can be considered racist, sexist, homophobic, or generally offensive.

• Link for dataset: https://www.kaggle.com/mrmorj/hate-speech-and-offensive-language-dataset

---

Tools used for project development:

• Python

• NLP

• Porter Stemmer

• Count Vectorizer

• XGBoost Classifier

• Random Forest Classifier

• Decision Tree

• Support Vector Machine

• Logistic Regression

• K Nearest Neighbours

• Gaussian Naive Bayes Classifier

---

If you like this repo, please don't forget to give a ⭐.