#538 Project

In Fall 2022, I joined the Erdős Institute's Data Science Boot Camp, but started three weeks late as I was busy with teaching. Consequently, I missed the final project phase. Determined to complete a project, I embarked on a solo endeavor in February 2023, with valuable guidance from Erdős Institute staff. This project began in mid-March 2023 but was paused in April for another commitment, with brief revisits afterward.

About the Project: This project involves scraping data from the 1,000 most recent posts on FiveThirtyEight’s features page, capturing post type (article, video, or podcast), title, URL, authors, date and time posted, tags, and comment counts. The primary question I aim to answer is: What types of posts on FiveThirtyEight receive the most comments? See the ProblemStatement Jupyter notebook for more details.

Project Files:

• DataExploration Notebook: Contains the initial data exploration work. To manage length, I exported it as a .py file to import functions into the DataExplorationII notebook.
• ProblemStatementOutputs Folder: Holds output files from running the scraping code in the ProblemStatement notebook, used for exploratory analysis while debugging.
• FirstAttempts Folder: Contains files from my initial project on the effects of drug use on mental health during the COVID-19 pandemic, using Kaggle data. Despite abandoning the project due to low data quality, I retained these files as a learning resource in Python.

Explore this project to see how I analyze data from FiveThirtyEight and gain insights into post engagement.