Completed in Summer 2021 by Pruthvi Panati, Lavanya Narayanan, Xingtong Tang, Arielle Herman, Tianqing Zhou.
Challenge: The Black List is a platform for TV and film writers to showcase their screenplays for industry members and get their work evaluated by professional readers. Having accumulated a large number of scripts over the years, the challenge is to use these data in ways that help the mission of the organization, as well as provide service to the industry.
Problem Statement: Develop an exploratory tool to visualize some of the trends in the data, improve the tagging system, and provide a better understanding of how to measure quality and feedback.
Envisioned Outcome: A prototype of a dashboard for use by writers and producers interested in exploring the scripts, as well as an algorithm for classifying scripts.
Data: The Black List tags and describes the scripts by genre, roles, characters, and other characteristics, collects data on the writers, and collects quantitative and qualitative feedback from professional readers.
Solution: The team explored three avenues for analysis. First, they consolidated some of the tags associated with scripts and looked for patterns of how tags appear together: which ones often appear together and which one never appear together. Next, the team explored and visualized gender and race representation in movie scripts. Finally, the team developed an algorithm to predict script similarity based on various characteristics such as genre, roles, topics, and more.