As the world begins to become more aware of the oppression that minority groups face, representation in the film industry, both on and off screen, has become an increasingly pressing issue.
We want to discover if the film industry has made substantial systemic changes to evolve along with society.
Using the CMU Movie Summary Corpus dataset, Kaggle’s Movie Datasets, and IMDB’s Movie Datasets, we will compare the character metadata and crew data of older films to that of more recent films and see disparities in ethnicity and gender using a paired t-test.
Further, we can analyze the movie summaries in the CMU datasets to compare how important minority characters to the storyline compared to their co-characters by applying coreference resolution to measure how often they are mentioned in the film plot.
These analyses will determine if there have been significant changes in the film industry over time.