Seeded Topic Models in Digital Archives: Analyzing Interpretations of Immigration in Swedish Newspapers, 1945–2019
Sociological Methods & Research · 2026-02 · 55 (1) · 120-156
DOI: 10.1177/00491241241268453 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sociological Methods & Research, online erschienen am 22.08.2024. Verfasst von Miriam Hurtado Bodell und 2 weiteren Autor:innen. Die Arbeit wurde bisher 11-mal zitiert (Crossref) und nennt 145 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Vetenskapsrådet.
Abstract (Originalsprache)
Sociologists are discussing the need for more formal ways to extract meaning from digital text archives. We focus attention on the seeded topic model, a semi-supervised extension to the standard topic model that allows sociological knowledge to be infused into the computational learning of meaning structures. Seed words help crystallize topics around known concepts, while utilizing topic models’ functionality to identify associations in text based on word co-occurrences. The method estimates a concept’s shared interpretation (or framing) via its associations with other frequently co-occurring topics. In a case study, we extract longitudinal measures of media frames regarding immigration from a vast corpus of millions of Swedish newspaper articles from the period 1945–2019. We infer turning points that partition the immigration discourse into meaningful eras and locate Sweden’s era of multicultural ideals that coined its tolerant reputation.
Förderung
- Vetenskapsrådet
Zitieren
APA
Bodell, M. H., Magnusson, M., & Keuschnigg, M. (2026). Seeded Topic Models in Digital Archives: Analyzing Interpretations of Immigration in Swedish Newspapers, 1945–2019. Sociological Methods & Research, 55(1), 120-156. https://doi.org/10.1177/00491241241268453
Vancouver
Bodell MH, Magnusson M, Keuschnigg M. Seeded Topic Models in Digital Archives: Analyzing Interpretations of Immigration in Swedish Newspapers, 1945–2019. Sociological Methods & Research. 2026;55(1):120-156. doi:10.1177/00491241241268453
BibTeX
@article{Bodell2026,
author = {Bodell, Miriam Hurtado and Magnusson, Måns and Keuschnigg, Marc},
title = {Seeded Topic Models in Digital Archives: Analyzing Interpretations of Immigration in Swedish Newspapers, 1945–2019},
journal = {Sociological Methods & Research},
year = {2026},
volume = {55},
number = {1},
pages = {120--156},
doi = {10.1177/00491241241268453}
}
EUVIMED