用AI自动生成美国总统竞选广告的字幕和摘要，覆盖1952-2012年共9707条视频。
Using AI to Summarize US Presidential Campaign TV Advertisement Videos, 1952-2012
- 构建大规模并行AI流水线，自动处理视频转录与摘要生成。
- 对9707条历史广告进行分析，人工评估显示质量媲美人工成果。
- 开源工具链可复用于其他视频数据集，助力政治传播研究。
本文发布了迄今为止最大、最全面的美国总统竞选电视广告数字数据集，包含可机器检索的字幕与高质量摘要，支持多种学术研究。过去研究受限于手动采集与标注，常依赖小规模样本。我们设计了一套大规模并行化AI分析流程，自动化完成视频处理、转录与摘要生成。该方法应用于朱利安·P·坎特政治广告档案（Julian P. Kanter Political Commercial Archive）中的9,707条总统竞选广告。通过广泛的人工评估，验证了自动生成的字幕与摘要在质量上可媲美人工成果。我们进一步展示了该数据的价值：追踪七十年间竞选议题的起源与演变。此外，本研究还提供了可复用的代码库，展示如何利用大语言模型为其他视频数据集生成高质量摘要。
原文摘要 · Abstract (English)
This paper introduces the largest and most comprehensive dataset of US presidential campaign television advertisements, available in digital format. The dataset also includes machine-searchable transcripts and high-quality summaries designed to facilitate a variety of academic research. To date, there has been great interest in collecting and analyzing US presidential campaign advertisements, but the need for manual procurement and annotation led many to rely on smaller subsets. We design a large-scale parallelized, AI-based analysis pipeline that automates the laborious process of preparing, transcribing, and summarizing videos. We then apply this methodology to the 9,707 presidential ads from the Julian P. Kanter Political Commercial Archive. We conduct extensive human evaluations to show that these transcripts and summaries match the quality of manually generated alternatives. We illustrate the value of this data by including an application that tracks the genesis and evolution of current focal issue areas over seven decades of presidential elections. Our analysis pipeline and codebase also show how to use LLM-based tools to obtain high-quality summaries for other video datasets.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。