A semantic similarity search engine for movies

Abstract

Semantic similarity has been gaining traction in the field of natural language processing. It is a measure of how similar two pieces of text are in terms of their meaning. It can be used to improve search engine results. We propose a deep learning-based approach to build a semantic similarity search engine for movies based on a movie summary. Filmmakers can gain insight into audience preferences and trends, allowing them to create more engaging and successful films. The dataset used in this study was gathered from internet movie database (IMDb), it includes movie summaries along with their corresponding name movies. The test dataset was generated using ChatGPT to be very close to human input. The universal sentence encoder (USE) model presented promising results in semantic similarity, the model results show that for the top 5 similar movies, the model returned 176 out of 300 movies (58.6%). For the top 10 similar movies, the model returned 211 out of 300 movies (70.3%). Additionally, for the top 15 similar movies, the model returned 229 out of 300 movies (76.3%). And, for the top 20 similar movies, the model returned 249 of 300 movies (83%). This method can be applied to movie recommendation systems or to organize films in a collection automatically.