Imagined Homelands in Print: AI-Based Text Segmentation and Register Analysis of the Finnish-American Press, 1876–1923.
This article presents a study on the use of artificial intelligence to analyze Finnish-language newspapers published in North America between 1876 and 1923. Using GPT-4 and LLaMA 3.1, we develop and evaluate a text segmentation method on large-scale digitized historical data, and we propose a hierar...
| Publicado en: | Digital Humanities in the Nordic & Baltic Countries Publications (DHNB Publications) Vol. 7; no. 4; pp. 1 - 13 |
|---|---|
| Autores principales: | , , , |
| Formato: | Artículo |
| Publicado: |
University of Oslo
2025
|
| Materias: | |
| Acceso en línea: | Ver este registro en EBSCOhost |
| fields | @attributes: recordID: 1 pdfLink: plink: https://search.ebscohost.com/login.aspx?direct=true&db=hlh&AN=191754544&site=ehost-live header: @attributes: shortDbName: hlh uiTerm: 191754544 longDbName: Humanities International Complete uiTag: AN controlInfo: bkinfo: jinfo: jid: 27041441 NUGX jtl: Digital Humanities in the Nordic & Baltic Countries Publications (DHNB Publications) issn: 27041441 maglogo: N pubinfo: dt: 2025 vid: 7 iid: 4 pid: 58757 pub: University of Oslo artinfo: ui: 191754544 ppf: 1 ppct: 12 formats: tig: atl: Imagined Homelands in Print: AI-Based Text Segmentation and Register Analysis of the Finnish-American Press, 1876–1923. aug: au: Skantsi, Valtteri Paju, Petri Salmi, Hannu Laippala, Veronika affil: University of Turku. University of Oulu. su: Text processing (Computer science) Digital humanities Newspapers Classification Genre studies Generative pre-trained transformers North America sug: subj: North America Text processing (Computer science) Digital humanities Newspapers Classification Genre studies Generative pre-trained transformers keyword: digital humanities historical newspapers register analysis register classification text segmentation ab: This article presents a study on the use of artificial intelligence to analyze Finnish-language newspapers published in North America between 1876 and 1923. Using GPT-4 and LLaMA 3.1, we develop and evaluate a text segmentation method on large-scale digitized historical data, and we propose a hierarchical taxonomy for register (genre) classification based on manual annotation. We present a methodology for identifying text boundaries and, separately, a manually developed register taxonomy used to classify segments. Our analysis is grounded in a manually annotated stratified corpus of 500 documents selected from 312,300 digitized pages. Results demonstrate strong segmentation accuracy, contributing both to digital humanities methodology and the historical understanding of the Finnish-American immigrant press. pubtype: Academic Journal doctype: Article src: R language: English refInfo: copyright: @attributes: flag: Y dt: @attributes: year: 2025 holdings: @attributes: islocal: N |
|---|