Brice Valentin Kok - Shun Department of Information Systems and Operations Management University of Auckland Auckland, New Zealand 0000 - 0001 - 9923 - 5042 Johnny Chan Department of Information Systems and Operations Management University of Auckland Auckland, New Zealand 0000 - 0002 - 3535 - 4533 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 collect ion 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 ca tegory identification . The results revealed a significant prevalence of product - related ads across vari ous educational topics, with ad categories refined using GPT - 4 o 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. T his study highlights the potential of LLMs in transforming ad detection processes and improving our understanding of ad vertisement strategies in digital media. In recent years, video - sharing platforms like YouTube have become dominant sources of entertainment, education, and information [1] . YouTube is invaluable for content creators, marketers, and advertisers. One of the key features of YouTube's revenue model is the integration of sponsored advertisement (ad) segments, which allows content creators to monetize their videos while providing advertisers a direct route to target specific audiences [2] .

Look-Alike modeling is one of the most popular methods for expanding the size of ad segments to provide advertisers increased reach. Facebook introduced Look Alike modeling to its platform in 2013 and several ad-tech providers offer a version of look-alike modeling natively within their products. However, as we will show in this post, Look Alike models in practice often result in brittle and inaccurate segments. A variety of other machine learning (ML) approaches -- including classification and uplift -- almost always yield superior performance compared to Look Alike models. Because of these limitations, we believe Look Alikes should be used sparingly, only when other techniques are unavailable.