Proposing a Semantic Movie Recommendation System Enhanced by ChatGPT's NLP Results

2025-07-29

AI Summary

Existing movie recommendation systems predominantly rely on explicit genre labels, limiting their ability to capture deep semantic information from textual descriptions and users’ latent preferences, thereby compromising personalization. To address this, we propose a semantic-enhanced recommendation framework integrating large language models (LLMs) and knowledge graphs. Specifically, we leverage ChatGPT to parse movie synopses and extract fine-grained sentiment orientations and semantic features; construct a semantics-enriched movie knowledge graph that encodes implicit cross-film associations; and incorporate these semantic embeddings into a collaborative filtering framework for robust preference modeling. Experimental results demonstrate that our approach significantly outperforms conventional label-based methods in both accuracy (e.g., Recall@10, NDCG@10) and diversity (e.g., intra-list distance), validating the effectiveness of a semantics-driven paradigm in enhancing recommendation personalization and interpretability.

Technology Category

Data Mining & Knowledge Management: Conversational Systems for Recommendation & RetrievalMachine Learning: Learning Preferences or RankingsNatural Language Processing: Sentence-level Semantics, Textual Inference, etc.

Application Category

Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMsUser Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendationSearch and Retrieval-Augmented AI: Large language models for search

Abstract

The importance of recommender systems on the web has grown, especially in the movie industry, with a vast selection of options to watch. To assist users in traversing available items and finding relevant results, recommender systems analyze operational data and investigate users' tastes and habits. Providing highly individualized suggestions can boost user engagement and satisfaction, which is one of the fundamental goals of the movie industry, significantly in online platforms. According to recent studies and research, using knowledge-based techniques and considering the semantic ideas of the textual data is a suitable way to get more appropriate results. This study provides a new method for building a knowledge graph based on semantic information. It uses the ChatGPT, as a large language model, to assess the brief descriptions of movies and extract their tone of voice. Results indicated that using the proposed method may significantly enhance accuracy rather than employing the explicit genres supplied by the publishers.

Problem

• Enhancing movie recommendations using semantic analysis
• Leveraging ChatGPT to extract movie tone from descriptions
• Improving accuracy beyond traditional genre-based methods

Innovation

• Semantic knowledge graph for movie recommendations
• ChatGPT extracts tone from movie descriptions
• Enhances accuracy beyond explicit genre labels