Studying Comics at Scale with Artificial Intelligence: The PAGE Framework and Three Studies of American Comics and Japanese Manga
Researchers propose PAGE, an AI framework that parses and annotates thousands of American comics and Japanese manga.
The paper proposes PAGE, a framework that uses AI as an instrument for comics research. It parses scans into panels, text, and bibliographic records, then annotates pages with a vision-language model following a written codebook and checks samples against human annotation. The authors apply it to 3,929 American comic books from 1938-1956 and 87 volumes of Japanese manga in studies of political portrayal, visual form and artist style, and who speaks. They also argue the tools can support archive search, accessibility, preservation, and credit for uncredited artists.
- PAGE parses comics into panels, text, and bibliographic records.
- A vision-language model annotates pages using a written codebook.
- Studies cover 3,929 American comics (1938-1956) and 87 manga volumes.
- Uses include archive search, accessibility, preservation, and artist credit.
- Countries
- United StatesJapan
From the original article
1 min read at arxiv.orgComics are one of the great visual records of the twentieth century: hundreds of thousands of pages in which a mass readership saw its leaders, its wars and its heroes. Most of this record has never been studied as a whole; comics scholarship proceeds one book at a time. We argue that artificial intelligence, including generative models, can change this to the benefit of the medium itself.
By Emilio Ferrara · arxiv.org
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.