https://github.com/bghorvath/TextMiningTheBechdelTest

Text mining movie scripts to explore long-term trend of female representation in movies according to the Bechdel test
https://github.com/bghorvath/TextMiningTheBechdelTest

bechdel bechdel-test coreference-resolution neuralcoref spacy

Last synced: 2 months ago
JSON representation

Text mining movie scripts to explore long-term trend of female representation in movies according to the Bechdel test

• Host: GitHub
• URL: https://github.com/bghorvath/TextMiningTheBechdelTest
• Owner: bghorvath
• Created: 2021-05-21T19:11:55.000Z (over 3 years ago)
• Default Branch: main
• Last Pushed: 2021-07-05T21:35:28.000Z (over 3 years ago)
• Last Synced: 2024-04-22T13:31:05.223Z (9 months ago)
• Topics: bechdel, bechdel-test, coreference-resolution, neuralcoref, spacy
• Language: Python
• Homepage:
• Size: 6.18 MB
• Stars: 1
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
## Text mining movie scripts to perform the Bechdel test using spaCy

The Bechdel test is a measure of representation of women in fiction. It asks whether a work features at least two female characters who talk to each other about something other than a man.  

Within the framework of this project I used text mining techniques on 1500+ movie scripts that I downloaded/parsed from the internet to explore long-term trend of female representation in movies by performing the test on them.

Data files can be downloaded from:  

https://drive.google.com/drive/folders/1konx-AYGYk2zGTdHR97vgQAl_IB2r9Q2

Data files not included:

- Raw, unprocessed movie scripts (2071 txt/pdf/rtf/doc file, ~1.1GB) - can be downloaded through .py files

- Results evaluation from 3 judges

- Exported CSV files

The project report can be accessed at:

https://www.dropbox.com/s/96czpl7e5xerhtp/IRTM_project_report.pdf?dl=0

Inspirations for the data structures were taken from:

https://www.youtube.com/watch?v=jRKKPYDs44o