Welcome to the Multi-Label Movie Genre Classification project! This repository contains code and resources for predicting movie genres based on plot summaries. It was developed for the AI Club's hackathon, focusing on multi-label classification tasks.
In this project, we explore the unique challenge of predicting multiple genres for movies using machine learning techniques. The dataset consists of plot summaries paired with genre labels, spanning a diverse range of genres including action, comedy, drama, horror, romance, sci-fi, and more.
data/: Contains the dataset with plot summaries and genre labels.notebooks/: Jupyter notebooks for data preprocessing, feature engineering, model training, and evaluation.models/: Trained models and model evaluation metrics.requirements.txt: List of Python dependencies.
- Clone this repository:
git clone https://github.com/asharam582/multi-label-movie-genre-classification.git
cd multi-label-movie-genre-classification
-
Install dependencies:
-
pip install -r requirements.txt
-
Explore the notebook for data preprocessing, model training, and evaluation.
-
Experiment with different models, feature engineering techniques, and hyperparameters to improve performance.
-
Collaborate with the community and share your insights!
We evaluate model performance using the F1 score, which combines precision and recall for multi-label classification tasks. The goal is to build accurate and efficient classification models capable of predicting movie genres from plot summaries.
Contributions to this project are welcome! If you have ideas for improvements or new features, feel free to open an issue or submit a pull request.
This project is licensed under the MIT License - see the LICENSE file for details.