Comparative NLP analysis of prosperity theology videos vs. non-prosperity evangelical controls.
- Push this repo to GitHub (create a new repo and push).
- Go to share.streamlit.io and sign in with GitHub.
- Click New app.
- Configure:
- Repository:
chaiboo/propserity(or your repo name) - Branch:
main - Main file path:
dashboard.py
- Repository:
- Click Deploy. The app will install dependencies and run the dashboard.
The corpus data (data/processed/corpus.csv) is included in the repo, so the dashboard works without running the corpus builder.
# Create virtual environment
python -m venv .venv
source .venv/bin/activate # Windows: .venv\Scripts\activate
# Install dependencies
pip install -r requirements.txt
# Run dashboard (corpus must exist)
streamlit run dashboard.pyTo build or rebuild the corpus (requires YouTube API key):
export YT_API_KEY='your-key'
python build_corpus.py --freshdashboard.py— Streamlit appbuild_corpus.py— Scrapes transcripts and builds corpusanalysis/— NLP features, lexicons, topicsdata/processed/corpus.csv— Combined YouTube corpus