Shadfa 0.1: The Iranian Movie Knowledge Graph and Graph-Embedding-Based Recommender System

TL;DR

This paper introduces Shadfa 0.1, an Iranian movie knowledge graph and a graph-embedding-based recommender system that combines TF_IDF and knowledge graph embeddings, optimized with a genetic algorithm, to improve movie recommendations.

Contribution

It presents a novel weighted content-based movie recommender system integrating TF_IDF and knowledge graph embeddings with genetic algorithm optimization, and creates a new Iranian movies dataset and knowledge graph.

Findings

The proposed system outperforms traditional TF_IDF-only approaches in accuracy.

The combination of TF_IDF and KGE improves recommendation quality.

The Iranian movies dataset and MovieFarsBase KG support effective content-based recommendations.

Abstract

Movies are a great source of entertainment. However, the problem arises when one is trying to find the desired content within this vast amount of data which is significantly increasing every year. Recommender systems can provide appropriate algorithms to solve this problem. The content_based technique has found popularity due to the lack of available user data in most cases. Content_based recommender systems are based on the similarity of items' demographic information; Term Frequency _ Inverse Document Frequency (TF_IDF) and Knowledge Graph Embedding (KGE) are two approaches used to vectorize data to calculate these similarities. In this paper, we propose a weighted content_based movie RS by combining TF_IDF which is an appropriate approach for embedding textual data such as plot/description, and KGE which is used to embed named entities such as the director's name. The weights between features are determined using a Genetic algorithm. Additionally, the Iranian movies dataset is created by scraping data from movie_related websites. This dataset and the structure of the FarsBase KG are used to create the MovieFarsBase KG which is a component in the implementation process of the proposed content_based RS. Using precision, recall, and F1 score metrics, this study shows that the proposed approach outperforms the conventional approach that uses TF_IDF for embedding all attributes.