- Public Policies and Public Opinions Behind New York Times News Articles in Four Years
Final project for the MACS 31300: AI Applications in social Science course in which I scraped the NYT times data in 1971, 1989, 2010, and 2020 and applied a mix of natural language processing, machine learning, and deep learning algorithms to investigate the questions of what words went viral in those time points and if their popularities were triggered by social, political, or judicial events of that year.
$\textbf{skills}$: data cleaning (pandas), web scraping (request), natural language processing (nltk, gensim, collections), machine learning (scipy etc.), deep learning (Tensorflow), Google Colab, data visualization (seaborn)
Available at (https://github.com/jcvincentliu/MACS-31300-Final-Project-Diving-into-NYT-News-Articles-at-Four-Time-Points/blob/main/project.ipynb)
- Crime in the Hood
Final group project for the CAPP 30122: Computer Science with Applications II class in which I was responsible for creating interactive visualizations that shed light on the crime and food resource situations in Chicago’s 77 neighborhoods as well as how they changed in the recent 20 years. All visualizations are presented in a jupyter notebook file. I also supported my teammates' works on web scraping, machine learning (decision tree), and Python Dash development.
$\textbf{skills}$: data cleaning (pandas), interactive data visualization (Plotly, seaborn), web scraping (request, beautifulsoup4), machine learning (scipy, statsmodel, sklearn)
Available at (https://github.com/jcvincentliu/CAPP-30122-Final-Project-Food_in_the_Hood)