How sushant2103-afk/hate-speech-and-offensive-language-detection works
This repository is a notebook-based workflow for classifying labeled tweets into three classes. The documented path runs from loading and inspecting the dataset through text cleaning, stopword removal and stemming, then vectorization and a train/test split. Decision Tree and Random Forest models are trained and evaluated with classification metrics and a confusion-matrix heatmap. The notebook is the only implementation file in the tree. Relationships and stages below are based on the README; no notebook source excerpts were available to verify finer-grained calls.
Main entry points: Project_1_Hate_Speech_Detection.ipynb Vectorize and split
Components 10
Data preparation
- Inspect and filter
Project_1_Hate_Speech_Detection.ipynb - Clean tweet text
Project_1_Hate_Speech_Detection.ipynb - Remove stopwords and stem
Project_1_Hate_Speech_Detection.ipynb - Vectorize and split
Project_1_Hate_Speech_Detection.ipynb
Classification and evaluation
- Decision Tree
Project_1_Hate_Speech_Detection.ipynb - Random Forest
Project_1_Hate_Speech_Detection.ipynb - Evaluate predictions
Project_1_Hate_Speech_Detection.ipynb - Confusion matrix heatmap
Project_1_Hate_Speech_Detection.ipynb
Other components
- Notebook user
- Labeled tweets
Connections 10
- Notebook user → Inspect and filter: runs notebook
README.md - Labeled tweets → Inspect and filter: provides tweets
README.md - Inspect and filter → Clean tweet text: selects text
README.md - Clean tweet text → Remove stopwords and stem: passes cleaned text
README.md - Remove stopwords and stem → Vectorize and split: passes processed text
README.md - Vectorize and split → Decision Tree: provides split features
README.md - Vectorize and split → Random Forest: provides split features
README.md - Decision Tree → Evaluate predictions: provides predictions
README.md - Random Forest → Evaluate predictions: provides predictions
README.md - Evaluate predictions → Confusion matrix heatmap: renders matrix
README.md