How nishahussain03-afk/cyberbullying-detection-project works
This repository provides a Streamlit app that accepts text, cleans it, combines a TF-IDF/model prediction with a keyword check, and displays a detection result. The README also describes model training and includes a dataset and notebook; their implementation details and connections are not shown in the sampled source, so they are represented as a separate development branch without inferred data-flow edges.
Main entry points: app.py Streamlit app · tfidf_vectorizer.pkl TF-IDF vectorizer · cyberbullying_model.pkl Classifier model
Components 10
Web application
- Streamlit app
app.py - Displayed result
app.py
Text inference
- Text cleaning
app.py - TF-IDF vectorizer
tfidf_vectorizer.pkl - Classifier model
cyberbullying_model.pkl - Keyword check
app.py - Final decision
app.py
Training assets
- Training dataset
dataset.csv - Training notebook
Cyberbullying_web.ipynb
Other components
- User
Connections 12
- User → Streamlit app: enters text
- Streamlit app → Text cleaning: cleans text
- Streamlit app → TF-IDF vectorizer: transforms text
- Text cleaning → TF-IDF vectorizer: cleaned text
- Streamlit app → Classifier model: predicts
- TF-IDF vectorizer → Classifier model: feature vector
- Streamlit app → Keyword check: checks keywords
- Streamlit app → Final decision: applies decision
- Classifier model → Final decision: prediction
- Keyword check → Final decision: keyword match
- Final decision → Displayed result: selects message
- Streamlit app → Displayed result: displays result