Women, Dialogue and the Box Office

Built a regression model to explore the impact of gender bias in the movie industry on box office revenue. Analysis and modeling done with pandas, statsmodel and scikit-learn. Visualizations created using matplotlib and seaborn. Data scraped from Box Office Mojo and bechdeltest.com using Beautiful Soup, queried from the OMDB API and obtained from Polygraph's Film Dialogue Dataset.

Blog post

Presentation

Data Sources:

• Box Office Mojo
• Bechdel Test
• OMDB (Open Movie Database)
• Polygraph’s Film Dialogue Dataset