Analytics of The Oscars: Best Picture Nominee Word Clouds

 

Oscar nominations for 2017 will be revealed on January 23. As a tribute to the award-giving body, let’s do some basic text analytics on Oscar-worthy films.

In this two-part post, we look at word clouds made out of plot summaries from Best Picture nominees and winners in the 1928 Oscars ceremony up to 2016.

Plot summaries were scraped from Wikipedia with Beautiful Soup and subsequently processed with Pandas, Textblob and NLTK. Only nouns, adjectives and verbs were retained, and proper nouns and stop words were filtered out. Check out the Jupyter notebook here.

Here are the word clouds for Best Picture nominees, partitioned by decade.

nominee_1920snominee_1930snominee_1940snominee_1950snominee_1960snominee_1970snominee_1980snominee_1990snominee_2000snominee_2010s

See something interesting? What are your 2018 Best Picture nominees? Leave a comment below.

One thought on “Analytics of The Oscars: Best Picture Nominee Word Clouds

Leave a Reply