/Skybug-Movie-Genre-Classification

Use of textual descriptions to classify movies into genres through BERT tokenization and classification models

Primary LanguageJupyter NotebookMIT LicenseMIT

Skybug-Movie-Genre-Classification

The aim of this project is to use textual description of a movie's plot/summary to classify it into genres.

Data Description

  • train_data.txt - includes movie name, genre and summary for training
  • test_data.txt - includes movie name, summary for testing
  • test_data_solution.txt - includes movie name, genre and summary for testing
  • x_train.csv & x_test.csv - processed input data
  • train_data_with_languages.csv - training data with summary languages
  • y_train.csv & y_test.csv - processed output data

Link - https://drive.google.com/drive/folders/1GRLCoSIivAdBw03oC2S8NxNCpn4sHJ3I?usp=drive_link