How yuvraj-bansal/fake-job-postings works
This is a Streamlit fake-job-posting detector. Users enter a posting manually or provide a URL for scraping, then compare baseline and DistilBERT fake-probability predictions and receive risk guidance and suspicious-phrase explanations. The README documents both model paths; sampled code confirms the scraper, inference helpers, and explanation utilities. Some app sections and subsystem internals were not sampled, so their documented relationships are cited to the README rather than inferred from imports.
Main entry points: app.py Streamlit interface · scraper.py Posting scraper · model.py TF-IDF baseline · explainer.py Red-flag explanations
Components 15
Posting intake
- Streamlit interface
app.py - Posting scraper
src/scraper.py
Detection models
- Text cleaning
src/preprocess.py - Structured features
src/features.py - TF-IDF baseline
src/model.py - Baseline artifacts
src/lr_model.pkl - DistilBERT text format
src/model.py - DistilBERT inference
src/model.py - Fake probabilities
src/model.py
Risk interpretation
- Red-flag explanations
src/explainer.py - Risk assessment
src/explainer.py - Safety tips and highlights
app.py
Other components
- Job seeker
- Job-board pages
- Hugging Face Hub
Connections 19
- Job seeker → Streamlit interface: enters posting
README.md - Streamlit interface → Posting scraper: requests scrape
app.py - Posting scraper → Job-board pages: fetches pages
src/scraper.py - Posting scraper → Streamlit interface: returns fields
README.md - Streamlit interface → Text cleaning: cleans text
README.md - Streamlit interface → Structured features: extracts features
README.md - Streamlit interface → TF-IDF baseline: runs prediction
README.md - TF-IDF baseline → Baseline artifacts: loads artifacts
src/model.py - Streamlit interface → DistilBERT text format: builds model text
README.md - Streamlit interface → DistilBERT inference: runs prediction
app.py - DistilBERT inference → Hugging Face Hub: loads model
src/model.py - TF-IDF baseline → Fake probabilities: returns probability
src/model.py - DistilBERT inference → Fake probabilities: returns probability
src/model.py - Streamlit interface → Red-flag explanations: finds red flags
app.py - Streamlit interface → Risk assessment: maps probability
app.py - Red-flag explanations → Structured features: uses keyword lists
src/explainer.py - Streamlit interface → Safety tips and highlights: renders advice
app.py - Streamlit interface → Fake probabilities: displays comparison
README.md - Risk assessment → Safety tips and highlights: informs guidance
app.py