August 2023
Created a method to flag duplicate accounts through NLP and cluster analysis
Tools: Python, pandas, SQL, R, SciPy, Tableau
Portfolio
June 2023
Created quantitative measures to assess referee bias
Tools: Python, NLTK, pandas, scikit-learn, SciPy, Matplotlib
Work in Progress
Created algorithm to identify cultural areas with NLP and HDBSCAN
Tools: Python, OpenStreetMap, pandas, scikit-learn, JSON
Quantifying Media Slant: A Computational Method
Completed (writeup expected December 2023)
Created method to assess media bias through fine-tuning LLMs on sample text
Tools: Python, PyTorch, Hugging Face, Azure, pandas
