Fake News Detector
During my 5 week fellowship at Data Science for All Women’s Summit (Fall 2020), my teammates and I built a fake news detector using various natural language processing tools such as embeddings, RNN, BERT, and transfer learning. We performed careful preprocessing to remove biases in the dataset, and we used a model interpretability tool called LIME to identify points of improvement for our model.
Take a look at our code on GitHub!
Hospital bed shortage prediction due to COVID-19
Check out this COVID-19 hospital app I built!
The app predicts the dates during which hospitals in the US are expected to experience bed shortage due to COVID-19.
The app uses COVID-19 data from the Johns Hopkins CSSE repository to fit a SIR model. It also uses state-level demographic information and hospital capacity to predict the number of COVID-19 patients that will require hospital and ICU beds.
For details on the model, please read this medium post.
You can play around with the code on Google Colab.
Note: The app uses data that was available on March 26, 2020