ramtin-ehsani / movie-genre-nlp

Natural Language Processing Spring 2022 Final Project

Movie Genre NLP

Natural Language Processing Spring 2022 Final Project

Prediction of genres based on the plot of the movies

Phase 1

Tasks:

1. Data crawling from IMDB
2. Data pre-processing
3. Data analysis

During this phase, we crawled around 31K unique movies with different genres of IMDB, and pre-processed and cleaned the data for further phases down the road.

The data contains the following format:

Movie Title	Genres	Plot Summary

An example of the data we've crawled:

Movie Title	Genres	Plot Summary
Doctor Strange in the Multiverse of Madness	['Action', ' Adventure', ' Fantasy']	Doctor Strange teams up with a mysterious teenage girl from his dreams who can travel across multiverses, to battle multiple threats, including other-universe versions of himself, which threaten to wipe out millions across the multiverse. They seek help from Wanda the Scarlet Witch, Wong and others.

Libraries used for data scrapping:

• BeautifulSoup
• Requests