Web Archives Metadata Generation with GPT-4o: Challenges and Insights.
Saved in:
| Title: | Web Archives Metadata Generation with GPT-4o: Challenges and Insights. |
|---|---|
| Authors: | Nair, Ashwin, Zhen Rong Goh, Tianrui Liu, Yongping Huang, Abigail |
| Source: | Information Technology & Libraries; Jun2025, Vol. 44 Issue 2, p1-16, 16p |
| Subject Terms: | GENERATIVE artificial intelligence, WORLD Wide Web, ARCHIVES, DATABASES, COST control, COST effectiveness, DATABASE management, COMPUTER software, COMPUTERS, PRIVACY, NATURAL language processing, INTERNET, INFORMATION technology, DESCRIPTIVE statistics, BIOMEDICAL engineering, MOTIVATION (Psychology), METADATA, INFORMATION retrieval, AUTOMATION, COMPARATIVE studies, ALGORITHMS, DIGITAL libraries, NONPARAMETRIC statistics, MEDICAL ethics |
| Geographic Terms: | SINGAPORE |
| Abstract: | Current metadata creation for web archives is time consuming and costly due to reliance on human effort. This paper explores the use of GPT-4o for metadata generation within the Web Archive Singapore, focusing on scalability, efficiency, and cost effectiveness. We processed 112 Web ARChive (WARC) files using data reduction techniques, achieving a notable 99.9% reduction in metadata generation costs. By prompt engineering, we generated titles and abstracts, which were evaluated both intrinsically using Levenshtein distance and BERTScore, and extrinsically with human cataloguers using McNemar's test. Results indicate that while our method offers significant cost savings and efficiency gains, human curated metadata maintains an edge in quality. The study identifies key challenges including content inaccuracies, hallucinations, and translation issues, suggesting that large language models (LLMs) should serve as complements rather than replacements for human cataloguers. Future work will focus on refining prompts, improving content filtering, and addressing privacy concerns through experimentation with smaller models. This research advances the integration of LLMs in web archiving, offering valuable insights into their current capabilities and outlining directions for future enhancements. The code is available at https://github.com/masamune-prog/warc2summary for further development and use by institutions facing similar challenges. [ABSTRACT FROM AUTHOR] |
| Copyright of Information Technology & Libraries is the property of American Library Association and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) | |
| Database: | Complementary Index |
Full Text Finder 
Nájsť tento článok vo Web of Science Be the first to leave a comment!