YouTube video by MZES Methods Bites
Large Language Models for Social Research: Potentials and Challenges
π¨ Content alert π¨
New recording and workshop materials published!
β‘οΈ Large Language Models for Social Research: Potentials and Challenges
π€ @indiiigo.bsky.social (University of Mannheim)
πΊ youtu.be/p5wPJHK-74M
ποΈ github.com/SocialScienc...
06.11.2025 14:20 β π 9 π 3 π¬ 0 π 0
π #ACL2025NLP π¦πΉ @marlutz.bsky.social and I are presenting our poster on demographic representativeness of LLMs today!
π¦ 10:30-12:00
π Hall X5 (board 1 or 14 according to different sources π§)
Hereβs the paper on ACL anthology: aclanthology.org/2025.finding...
Drop by!
29.07.2025 07:31 β π 22 π 7 π¬ 0 π 1
Chair for Data Science in the Economic and Social Sciences at University of Mannheim having lots of fun at #ic2s2 @janajung.bsky.social @wanlo.bsky.social @indiiigo.bsky.social @jrupprec.bsky.social @maximiliankreutner.bsky.social and Stefano Balietti
23.07.2025 15:22 β π 21 π 4 π¬ 0 π 0
Really excited to also present this work at #IC2S2 next week in NorrkΓΆping! π I'd love to discuss how to produce LLM survey responses at my poster on Wed at 13:30 (Poster Session 2, Poster ID 68) π
18.07.2025 15:19 β π 18 π 6 π¬ 0 π 0
A research setup for the evaluation of Answer Production Methods for closed-ended survey responses from LLMs. An LLM is prompted with a survey and an optional instruction, before a Answer Production Method is applied. These methods range from token-probabilities to open-ended text generation + classification. I then evaluated them against human survey answers and calculate individual-level accuracy as well as distribution alignment for sub-populations.
LLMs are trained to produce open-ended responses π, but most survey items require closed-ended responses instead π
This Wed 11:00β12:30 at #ESRA25, I'll discuss the large impact that Answer Production Methods have on prediction results + share recommendations for methods and parameters. π
14.07.2025 13:34 β π 10 π 4 π¬ 0 π 2
Very excited to head to #IC2S2 next week! π
In our project, we tested whether a psychological assessment can measure sexism in LLMs, and found that applying such tools to LLMs is not as straightforward as it seems.
Find me and my poster at Poster Session 1 (Tue 12:30-14:30) β hope to see you there
17.07.2025 19:14 β π 9 π 4 π¬ 0 π 0
LLMs can generate synthetic survey responses, e.g. for imputation, but how reliable are they? π
At #IC2S2, I'll be sharing our research on the robustness of AI-generated responses to perturbations and if they mirror human survey biases. π€
Come by my poster on Tuesday between 1:30 and 3:30 p.m.
18.07.2025 14:16 β π 7 π 3 π¬ 0 π 0
The Milan Natural Language Processing Group #NLProc #AI
milanlproc.github.io
Political Science Postdoc // University of Salzburg // INCONEX // Party Leaders // part of the TaDa Reading Group - tada.cool // www.clintclaessen.com
Postdoc @milanlp.bsky.social / Incoming Postdoc @stanfordnlp.bsky.social / Computational social science, LLMs, algorithmic fairness
Uses machine learning to study literary imagination, and vice-versa. Likely to share news about AI & computational social science / Sozialwissenschaft / η€ΎδΌη§ε¦
Information Sciences and English, UIUC. Distant Horizons (Chicago, 2019). tedunderwood.com
Assistant Professor @ Princeton
Previously: EPFL π¨π, UFMG π§π·
Interests: Computational Social Science, Platforms, GenAI, Moderation
Postdoctoral fellow at ETH AI Center, working on Computational Social Science + NLP. Previously a PhD in CS at UMD, advised by Philip Resnik. Internships at MSR, AI2. he/him.
On the job market this cycle!
alexanderhoyle.com
AI Architect | North Carolina | AI/ML, IoT, science
WARNING: I talk about kids sometimes
Alexander von Humboldt Professor for AI and Chair for Societal Computing at Saarland University. Co-Director at https://i2sc.net.
The Conference of the European Chapter of the Association for Computational Linguistics
Next event: Rabat, Morocco, March 24-29, 2026
Hashtags: #EACL2026 #NLProc
The European Political Science Society: the not-for-profit professional association for political science in Europe and beyond
https://epssnet.org/
Assistant Professor in Computational Social Science at University of Amsterdam
Studying the intersection of AI, social media, and politics.
Polarization, misinformation, radicalization, digital platforms, social complexity.
Co-founder, Survey 160. Loves survey and voter participation. Researcher. Democrat. YIMBY. Husband and Dad. Opinion haver and measurer. Outdoors and cooking enthusiast. He/Him
Cognitive and decision science at MPI for Human Development & Uni Basel | Data science at therbootcamp.github.io | R, language models, and sustainability (text2sdg.io).
Professor of Computational Social Science @University of Mannheim & Scientific Director Department Computational Social Science @GESIS
https://sebastianstier.com
The official account of the Stanford Institute for Human-Centered AI, advancing AI research, education, policy, and practice to improve the human condition.
Computational Social Science researcher interested in Human Coordination and Climate Action. Professor of Data Science at the IT University of Copenhagen. Network Science | NLP | AI agents | Urban Informatics
http://www.lajello.com
Professor for Social and Behavioral Data Science at the University of Konstanz. Also at CSH Vienna, ETH Zurich and TU Graz.
@max@maxpe.todon.de
Principal Investigator at Barcelona Supercomputing Center
Sociologist, Prof. of Organizational Behavior at Stanford who studies culture | Co-director of the Computational Culture Lab | http://comp-culture.org
computational social scientist
