News

SODA Lab at the 80th AAPOR conference

2 Jun 2025

SODA AI Lab at the 80th AAPOR conference



Last month, members of the SODA Lab attended the 80th AAPOR Conference in St. Louis (May 14–16, 2025), presenting on topics ranging from algorithmic fairness to generative AI and social‐media analytics.

Their contributions fell into four thematic areas, each reflecting ongoing methodological innovations in survey research.
We extend our gratitude to all presenters for their high‐quality work.

All presentation materials - including abstracts, slides, and posters - are available upon request.

1. Machine Learning and Algorithmic Fairness in Survey Methodology

  • My Training Data May Need a Trainer: Examining the Role of Representation in Algorithmic Bias and Fairness Using the Total Survey Error Framework
    Christoph Kern, Patrick Schenk and Trent Buskirk
  • How ML‐Filtered Answer Options Shape Responses and Interactions in CATI Surveys
    Olga Kononykhina
  • Prediction‐Based Adaptive Designs for Reducing Attrition Rates and Bias in Panel Surveys
    Jack Collins, Saskia Bartholomäus, Tobias Gummer, Christoph Kern, and Bernd Weiß

2. Measuring Attitudes Toward Artificial Intelligence

  • Measuring Population Attitudes Towards AI: Development & Validation of a General AI Attitude Short‐Scale for Large Survey Panels
    Christoph Kern, Marcus Novotny, Wiebke Weber, and Frauke Kreuter

3. Generative AI Applications and Bias in Survey and Election Research

  • Human Preferences in Large Language Model Latent Space: A Technical Analysis on the Reliability of Synthetic Data in Voting Outcome Prediction
    Sarah Ball, Simeon Allmendinger, Frauke Kreuter, and Niklas Kühl.
    Their poster—recipient of the AAPOR Poster Award
  • Short Course: Fine‐tuning LLMs for Data Augmentation
    Tobias Gummer and Anna‐Carolina Haensch
  • GPT, Pretend You Are a Survey Researcher: Results from a Systematic Literature Review on the Use of LLMs in Survey Research
    Leah von der Heyde, Trent Buskirk, Florian Keusch, and Adam Eck
  • United in Diversity? Contextual Biases in LLM‐Based Predictions of the 2024 European Parliament Elections
    Leah von der Heyde, Anna‐Carolina Haensch, Alexander Wenz, and Bolei Ma

4. Secondary Data and Social Media Insights

  • Understanding Secondary Data Reporting: A Glimpse at TweetsCOV19 & Dreaddit
    Laura Young and Fiona Draxler
  • Uncovering Cognitive Difficulties through Tourangeau’s Cognitive Response Model Using Mouse Movements
    Lisa Bondo Andersen, Stefan Schneider, Tobias Wistuba, Arie Kapteyn, Ailin Liu, Bart Orriens, Felix Henninger, Sonja Greven and Frauke Kreuter