EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

An Image Is Worth K Topics: A Visual Structural Topic Model with Pretrained Image Embeddings

Matías Piqueras, Alexandra Segerberg, Matteo Magnani, Måns Magnusson, Nataša Sladoje

Political Analysis · 05.11.2026 · 1-20

DOI: 10.1017/pan.2026.10062 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Political Analysis, online erschienen am 05.11.2026. Verfasst von Matías Piqueras und 4 weiteren Autor:innen. Die Arbeit nennt 84 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Political scientists are increasingly interested in analyzing visual content at scale. However, the existing computational toolbox is still in need of methods and models attuned to the specific challenges and goals of social and political inquiry. In this article, we introduce a visual structural topic model (vSTM) that combines continuous image embeddings with a structural topic model. This has important advantages compared to existing approaches. First, continuous embeddings allow the model to capture the semantic complexity of images, which is relevant to the study of politics. A consequence of using continuous embeddings is that we can directly use off-the-shelf pretrained deep learning models, offering state-of-the-art performance in image analysis tasks while saving time, cost and resources. Second, the structural topic model provides the ability to analyze how topics and covariates are related, while maintaining a nuanced representation of images as a mixture of multiple topics. In our experiments, we show that the vSTM is able to identify topics that are interpretable, coherent and relevant to the study of online political communication.

Zitieren

APA

Piqueras, M., Segerberg, A., Magnani, M., Magnusson, M., & Sladoje, N. (2026). An Image Is Worth K Topics: A Visual Structural Topic Model with Pretrained Image Embeddings. Political Analysis, 1-20. https://doi.org/10.1017/pan.2026.10062

Vancouver

Piqueras M, Segerberg A, Magnani M, Magnusson M, Sladoje N. An Image Is Worth K Topics: A Visual Structural Topic Model with Pretrained Image Embeddings. Political Analysis. 2026:1-20. doi:10.1017/pan.2026.10062

BibTeX
@article{Piqueras2026,
  author = {Piqueras, Matías and Segerberg, Alexandra and Magnani, Matteo and Magnusson, Måns and Sladoje, Nataša},
  title = {An Image Is Worth K Topics: A Visual Structural Topic Model with Pretrained Image Embeddings},
  journal = {Political Analysis},
  year = {2026},
  pages = {1--20},
  doi = {10.1017/pan.2026.10062}
}
Kostenlos starten →