Improving Graph-Based Movie Recommender System Using Cinematic Experience

MDPI Applied Science 논문 게재

• (2022.01.28) Improving Graph-Based Movie Recommender System Using Cinematic Experience in Applied Science in MDPI
• (2022.01.20) Multi-Relational Stacking Ensemble Recommender System Using Cinematic Experience in IEEE BigComp2022, Code
• Author's Paper link: https://arxiv.org/abs/1904.12058
• Author's code: https://github.com/muhanzhang/IGMC
• Reference code: https://github.com/zhoujf620/Motif-based-inductive-GNN-training

Dependencies

• PyTorch 1.2+
• DGL 0.5 (nightly version)

Data

Movie data

• Rotten Tomatoes data : https://www.kaggle.com/stefanoleone992/rotten-tomatoes-movies-and-critic-reviews-dataset
• Amazon Movie data : http://jmcauley.ucsd.edu/data/amazon/

Training set for BERT

• Sentiment Analysis : https://www.kaggle.com/c/sentiment-analysis-on-movie-reviews
• Emotion Analysis : https://www.kaggle.com/praveengovi/emotions-dataset-for-nlp

How to run

• explicit_train_rotten.ipynb

Results

Dataset	Our code best of epochs
Rotten Tomatoes	0.8004
Amazon Movie	0.9621