From Titles to Genres: An Exploration of Machine Learning Techniques in Movie Classification

The application of machine learning models to identify the genre of movies based on their titles and overviews is explored in this research paper. The “Movie Title” dataset from Kaggle is the source of the data for this investigation. The study examines the data, carries out the necessary cleaning and manipulation, creates a word cloud to visualize frequently occurring terms, resamples the data for a better distribution of genres, and employs two models for genre prediction: BERT (Bidirectional Encoder Representations from Transformers) and TF-IDF (Term Frequency-Inverse Document Frequency). The performance of both models is evaluated using accuracy and/or loss metrics, and conclusions are drawn based on the findings.