Leveraging ChatGPT for Sponsored Ad Detection and Keyword Extraction in YouTube Videos

TL;DR

This paper explores using GPT-4 and related NLP tools to detect sponsored ads and extract keywords in YouTube videos, offering a scalable method to analyze ad content and categories within educational videos.

Contribution

It introduces a novel, scalable approach leveraging large language models for ad detection and categorization in YouTube videos, improving over traditional methods.

Findings

High prevalence of product-related ads in educational videos

GPT-4o effectively categorizes content and ads into specific categories

The method offers a scalable alternative for ad detection in digital media

Abstract

This work-in-progress paper presents a novel approach to detecting sponsored advertisement segments in YouTube videos and comparing the advertisement with the main content. Our methodology involves the collection of 421 auto-generated and manual transcripts which are then fed into a prompt-engineered GPT-4o for ad detection, a KeyBERT for keyword extraction, and another iteration of ChatGPT for category identification. The results revealed a significant prevalence of product-related ads across various educational topics, with ad categories refined using GPT-4o into succinct 9 content and 4 advertisement categories. This approach provides a scalable and efficient alternative to traditional ad detection methods while offering new insights into the types and relevance of ads embedded within educational content. This study highlights the potential of LLMs in transforming ad detection processes and improving our understanding of advertisement strategies in digital media.