Georg Ahnert
LightNews LightNews
banner
wanlo.bsky.social
Georg Ahnert
@wanlo.bsky.social
200 followers 410 following 15 posts
PhD Student in Social Data Science at University of Mannheim | LLMs and Surveys | georgahnert.de
Posts Replies Media Videos
wanlo.bsky.social
Really inspiring keynote by @lauraknelson.bsky.social this morning at #IC2S2 discussing when to model and when to generate societies—among many other themes in computational qualitative research!
Laura Nelson on stage presenting her keynote at IC2S2. The slide lays out "A maturing field" of Computational Qualitative Research
July 23, 2025 at 8:00 AM
wanlo.bsky.social
The 15.07 train has a 30 min delay now but the landscape‘s quite pretty ;)
The Swedish countryside as seen from a moving train, with a lake, a red and white house, and some cows.
July 20, 2025 at 4:19 PM
wanlo.bsky.social
LLMs are trained to produce open-ended responses 📝, but most survey items require closed-ended responses instead 📊

This Wed 11:00–12:30 at #ESRA25, I'll discuss the large impact that Answer Production Methods have on prediction results + share recommendations for methods and parameters. 👈
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.
July 14, 2025 at 1:34 PM
wanlo.bsky.social
Results: From several collective emotions and public opinion, our longitudinal estimates show a strong positive and significant cross-correlation with survey data gathered by YouGov directly from human participants.
Our estimates with Llama 3 Temporal Adapters show a strong positive and significant correlation with collective frustration, fear, boredom, and sadness. Our results vary strongly between emotions, but they are in line with a baseline method's estimates. We also apply our method to the extraction of public attitudes towards Boris Johnson as a prime minister and towards the National Healthy Service, were we similarly find positive cross-correlation with survey data for some but not all answer options.
June 16, 2025 at 8:23 AM
wanlo.bsky.social
Method: We gather weekly text data from a panel of Twitter users and fine-tune Temporal Adapters for Llama 3 8B with it. 🦙 We then prompt Llama with established survey questions, one week at a time, to extract longitudinal affect aggregates.
Overview of our method that shows how each week's Twitter data is used to train a separate Temporal Adapter, and how a weekly affect aggregate is then obtained from the LLM's token probabilities.
June 16, 2025 at 8:23 AM
wanlo.bsky.social
Excited to present our paper with @maxpe.bsky.social, @dgarcia.eu, and @mstrohm.bsky.social next week at #ICWSM! ✨

We extend social simulation with LLMs to a longitudinal setting by fine-tuning Temporal Adapters—here's how: 🧵
A lineplot that shows how scared people in the UK were over time, during the first COVID-19 lockdown. Our method (Llama 3 Temporal Adapters) produces similar estimates of as the survey data gathered by YouGov.
June 16, 2025 at 8:23 AM