An AI-powered solution for detecting and categorising sponsored ad segments in YouTube videos

IF 1.3 Q3 COMPUTER SCIENCE, SOFTWARE ENGINEERING
Johnny Chan, Brice Valentin Kok-Shun
{"title":"An AI-powered solution for detecting and categorising sponsored ad segments in YouTube videos","authors":"Johnny Chan,&nbsp;Brice Valentin Kok-Shun","doi":"10.1016/j.simpa.2025.100759","DOIUrl":null,"url":null,"abstract":"<div><div>This paper presents an AI-powered software solution for detecting and categorising sponsored advertisement segments in YouTube videos. By combining GPT-4 for ad identification, KeyBERT for keyword extraction, and custom prompts for grouping keywords into concise categories, the software provides a scalable and efficient alternative to traditional ad detection methods. It processes both auto-generated and manual transcripts, ensuring adaptability across varied contexts. The tool enables a deeper understanding of advertising strategies and ad-content alignment while maintaining ease of use and reproducibility. This work highlights the potential of AI in transforming digital advertisement analysis.</div></div>","PeriodicalId":29771,"journal":{"name":"Software Impacts","volume":"24 ","pages":"Article 100759"},"PeriodicalIF":1.3000,"publicationDate":"2025-04-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Software Impacts","FirstCategoryId":"1085","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S2665963825000193","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"COMPUTER SCIENCE, SOFTWARE ENGINEERING","Score":null,"Total":0}
引用次数: 0

Abstract

This paper presents an AI-powered software solution for detecting and categorising sponsored advertisement segments in YouTube videos. By combining GPT-4 for ad identification, KeyBERT for keyword extraction, and custom prompts for grouping keywords into concise categories, the software provides a scalable and efficient alternative to traditional ad detection methods. It processes both auto-generated and manual transcripts, ensuring adaptability across varied contexts. The tool enables a deeper understanding of advertising strategies and ad-content alignment while maintaining ease of use and reproducibility. This work highlights the potential of AI in transforming digital advertisement analysis.

Abstract Image

一个人工智能解决方案,用于检测和分类YouTube视频中的赞助广告段
本文提出了一种人工智能驱动的软件解决方案,用于检测和分类YouTube视频中的赞助广告片段。通过将GPT-4用于广告识别,KeyBERT用于关键字提取,以及将关键字分组为简明类别的自定义提示相结合,该软件提供了传统广告检测方法的可扩展且高效的替代方案。它可以处理自动生成的和手动生成的转录本,确保跨不同上下文的适应性。该工具可以更深入地了解广告策略和广告内容对齐,同时保持易用性和可再现性。这项工作强调了人工智能在改变数字广告分析方面的潜力。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
Software Impacts
Software Impacts Software
CiteScore
2.70
自引率
9.50%
发文量
0
审稿时长
16 days
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术官方微信