Join us in NYC May 25th to hear from Matt Daniels, founder of the data-driven storytelling site Polygraph. One of his latest projects examines film dialogue from 2,000 screenplays, broken down by gender and age. See the full project here.
In this talk,Mattwill, step-by-step, discuss the data scraping and cleaning process for computing dialogue by gender for 2,000 screenplays. He'll review the Python scripts and databases used to house nearly 4 million lines of dialogue, he'll discuss how he mapped the data to IMDB, and will also go over his approach to visualizing the data in D3. The focus for this talk is practical: pro-tips and best practices for how he managed his most messy, complex project to date.
Food and drinks will be provided. Hope to see you there!