Project introduction


Welcome to the website of our ADA project. Here you can find the Github repository to find all the calculations that led to the plots used during the analysis. To access to the core of this project click here, or if you want to learn more about the team it’s up there.

Choice of datasets and question

Among all the proposed datasets, we choose to retain the CMU movie summary corpus. This dataset gathers informations such as the movie title, its genre, the release date, the langage, the casting, but also a summary of the preprocessed with the Standford CoreNLP pipeline. With all these informations available, we chose to study the representation of stereotypes in cinema.