CSS at University of Stuttgart

Yesterday we had the pleasure to welcome @benjaminrohr.bsky.social to present his new work on the Weimar Republic!

We thank @s7css.bsky.social for the opportunity to present our work as well as @emilienschultz.bsky.social for his support on this project.

An image of the title and abstract.

Happy to share my new paper with Cat Dang Ton and @eollion.bsky.social on how to use generative LLMs for extracting information from textual data (conditionally accepted at Sociological Methods & Research)

Here's a rundown..

osf.io/preprints/so...

Today we had a joint meeting with our group and @demolabs.bsky.social to talk about current projects! We never thought about democracy on Mars - Thanks for the visit!

I'll get straight to the point.

We trained 2 new models. Like BERT, but modern. ModernBERT.

Not some hypey GenAI thing, but a proper workhorse model, for retrieval, classification, etc. Real practical stuff.

It's much faster, more accurate, longer context, and more useful. 🧵

Today, we had the pleasure to welcome @oms279.bsky.social to present on "Temporalities of Climate Change in U.S. Media (2000-2021)" at our departmental colloquium!

WithdrarXiv: A Large-Scale Dataset for Retraction Study Retractions play a vital role in maintaining scientific integrity, yet systematic studies of retractions in computer science and other STEM fields remain scarce. We present WithdrarXiv, the first larg...

😳 WithdrarXiv 🙏

- Dataset of 14K+ withdrawn arXiv papers
- associated retraction comments
- entire history through 09/24
- taxonomy of retraction reasons, from critical errors to policy violations
- WithdrarXiv-SciFy, enriched version w/ scripts for parsed full-text PDFs

arxiv.org/abs/2412.03775

The pleasure was ours!

Yesterday, @s7css.bsky.social invited me to present my dissertation at the University of Stuttgart. It was a blast — thanks to the chair of Prof. Heiberger for their invitation, the audience for their amazing feedback, and the city for their hospitality! I'd love to come back one day!

Policy Actors’ Struggle for Attention: The Role of Peer Networks in the Migration Discourse on Twitter (X) Policy actors (PAs) like nongovernmental organizations, political parties or governmental institutions strategically communicate on social media to gain attention and thus influence the public agenda....

🚨 New publication by Sara Hanke and Raphael Heiberger: Policy Actors’ Struggle for Attention. The Role of Peer Networks in the Migration Discourse on Twitter (X) #ComputationalSocialScience #CSS #SocialMedia #Policy

www.degruyter.com/document/doi...

🚀 We’re thrilled to announce the release of Pop2net, a powerful new #Python package developed by Marius Kaffai & Lukas Erhard! 🎉
(1/3)

🚨 We're excited to share the latest publication of our members @luerhard.bsky.social , Sara Hanke and Raphael Heiberger in Political Analysis: 'PopBERT: Detecting Populism and Its Host Ideologies in the German Bundestag'. Check it out here: doi.org/10.1017/pan.... #PoliticalScience #Populism

Today, we had the pleasure to welcome @hendrik-erz.de to present on "Economic Policymaking in U.S. Congress. Discursive Dynamics, 1960–1990" at our departmental colloquium!

Network community detection via neural embeddings - Nature Communications Approaches based on neural graph embeddings have shown their effectiveness for complex networks analysis, including link prediction and node classification. The authors uncover strengths and limi...

Check out our paper "Network community detection via neural embeddings" led by @skojaku.bsky.social (w Filippo Radicchi and Santo Fortunato)! www.nature.com/articles/s41...

We argue that n2v can encode community structure down to the detectability limit due to its connection to spectral embedding.

🚨 We're excited to share the latest publication of our members @luerhard.bsky.social , Sara Hanke and Raphael Heiberger in Political Analysis: 'PopBERT: Detecting Populism and Its Host Ideologies in the German Bundestag'. Check it out here: doi.org/10.1017/pan.... #PoliticalScience #Populism

With customizable contact layers, it offers flexibility and control for building realistic interaction structures.
Perfect for anyone working with #AgentBasedModeling in Python!
Learn more & try it out here: mariuzka.github.io/pop2net/
#NetworkModeling #ResearchSoftware (3/3)

Pop2net is designed to help researchers easily generate network models for agent-based simulations—filling the gap between unavailable empirical data and overly abstract models. (2/3)

🚀 We’re thrilled to announce the release of Pop2net, a powerful new #Python package developed by Marius Kaffai & Lukas Erhard! 🎉
(1/3)

Excited to start as an Assistant Professor at the Department of Network and Data Science at CEU in Vienna. I am deeply grateful to the scholars I met at University of Cologne, @unistuttgart.bsky.social, and Dan McFarland's Mimir Lab for their support, intellectual generosity and kindness. Thank you!

🚨New job alert from our colleagues at the University of Amsterdam! 🚨
workingat.vu.nl/vacancies/ph...

Policy Actors’ Struggle for Attention: The Role of Peer Networks in the Migration Discourse on Twitter (X) Policy actors (PAs) like nongovernmental organizations, political parties or governmental institutions strategically communicate on social media to gain attention and thus influence the public agenda....

🚨 New publication by Sara Hanke and Raphael Heiberger: Policy Actors’ Struggle for Attention. The Role of Peer Networks in the Migration Discourse on Twitter (X) #ComputationalSocialScience #CSS #SocialMedia #Policy

www.degruyter.com/document/doi...