Matías Piqueras
@matiaspiqueras.bsky.social
32 followers 72 following 1 posts
PhD student in Computer Science at Uppsala University working on developing computer vision models and methods relevant to the study of politics and society.
Posts Media Videos Starter Packs
Reposted by Matías Piqueras
lrossi.bsky.social
Luca Rossi @lrossi.bsky.social · 20d
#computationalsocialscience Our work on using VLLMs for semantic visual clustering is out on SSCR: journals.sagepub.com/doi/10.1177/...

There is a lot happening in the space of computational analysis of visual content as we acknowledge more and more the visual nature of contemporary communication.
Sage Journals: Discover world-class research
Subscription and open access journals from Sage, the world's leading independent academic publisher.
journals.sagepub.com
1 2 6
Reposted by Matías Piqueras
solmg.bsky.social
Sol Messing @solmg.bsky.social · 27d
7/ Kernel Approximation Ideal Point Poisson Factorization - scalable Bayesian ideological estimation from billions of observations, applied to 134 million TikTok comments to map ideology on the platform. @matiaspiqueras.bsky.social
Matías Piqueras (@matiaspiqueras.bsky.social)
PhD student in Computer Science at Uppsala University working on developing computer vision models and methods relevant to the study of politics and society.
matiaspiqueras.bsky.social
1 1
Reposted by Matías Piqueras
uu-polisci.bsky.social
Department of Government, Uppsala University @uu-polisci.bsky.social · Jun 3
Sophie Mainz has been awarded the John Sullivan Award for the best paper by a graduate student presented at any of the panels organized by the Elections, Public Opinion, and Voting Behavior section at last year’s APSA conference. Congratulations to @sophiemainz.bsky.social !
4 15
Matías Piqueras @matiaspiqueras.bsky.social · Apr 20
Sharing our new preprint "An Image is Worth K Topics: A Visual Structural Topic Model with Image Embeddings" with @mansmag.bsky.social @matmagnani.bsky.social Alexandra Segerberg and Nataša Sladoje. Available on ArXiv: arxiv.org/abs/2504.10004
6 9