Demystifying ChatGPT: How It Masters Genre Recognition

TL;DR

This study evaluates ChatGPT's ability to predict movie genres using text prompts and visual data, demonstrating its superior performance and potential for content analysis in NLP and multimodal applications.

Contribution

It provides a comprehensive analysis of ChatGPT's genre prediction capabilities and introduces a novel multimodal approach incorporating visual information from movie posters.

Findings

ChatGPT outperforms other LLMs in genre prediction without fine-tuning.

Fine-tuned ChatGPT achieves the best overall performance.

Incorporating visual data from posters enhances genre prediction accuracy.

Abstract

The introduction of ChatGPT has garnered significant attention within the NLP community and beyond. Previous studies have demonstrated ChatGPT's substantial advancements across various downstream NLP tasks, highlighting its adaptability and potential to revolutionize language-related applications. However, its capabilities and limitations in genre prediction remain unclear. This work analyzes three Large Language Models (LLMs) using the MovieLens-100K dataset to assess their genre prediction capabilities. Our findings show that ChatGPT, without fine-tuning, outperformed other LLMs, and fine-tuned ChatGPT performed best overall. We set up zero-shot and few-shot prompts using audio transcripts/subtitles from movie trailers in the MovieLens-100K dataset, covering 1682 movies of 18 genres, where each movie can have multiple genres. Additionally, we extended our study by extracting IMDb movie posters to utilize a Vision Language Model (VLM) with prompts for poster information. This fine-grained information was used to enhance existing LLM prompts. In conclusion, our study reveals ChatGPT's remarkable genre prediction capabilities, surpassing other language models. The integration of VLM further enhances our findings, showcasing ChatGPT's potential for content-related applications by incorporating visual information from movie posters.