Fynn Bachmann

Fynn Bachmann

Auto-generated profile, based on publicly available information

Fynn Bachmann

Affiliations Department of Informatics, University of Zurich, Zurich, Switzerland, Digital Society Initiative, University of Zurich, Zurich, Switzerland

Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications

22 May 2025 in PLOS ONE
Verified
Journal Article
Open access
PDF file
FBFynn Bachmann
Fynn Bachmann
DWDaan van der Weijden
Daan van der Weijden
LHLucien Heitz
Lucien Heitz
CSCristina Sarasua
Cristina Sarasua
ABAbraham Bernstein
Abraham Bernstein
Adaptive questionnaires dynamically select the next question for a survey participant based on their previous answers. Due to digitalisation, they have become a viable alternative to traditional surveys in application areas such as political science. One limitation, however, is their dependency on data to train the model for question selection. Often, such training data (i.e., user interactions) are unavailable a priori. To address this problem, we (i) test whether Large Language Models (LLM) can accurately generate such interaction data and (ii) explore if these synthetic data can be used to pre-train the statistical model of an adaptive political survey. To evaluate this approach, we utilise existing data from the Swiss Voting Advice Application (VAA) Smartvote in two ways: First, we compare the distribution of LLM-generated synthetic data to the real distribution to assess its similarity. Second, we compare the performance of an adaptive questionnaire that is randomly initialised with one pre-trained on synthetic data to assess their suitability for training. We benchmark these results against an “oracle” questionnaire with perfect prior knowledge. We find that an off-the-shelf LLM (GPT-4) accurately generates answers to the Smartvote questionnaire from the perspective of different Swiss parties. Furthermore, we demonstrate that initialising the statistical model with synthetic data can (i) significantly reduce the error in predicting user responses and (ii) increase the candidate recommendation accuracy of the VAA. Our work emphasises the considerable potential of LLMs to create training data to improve the data collection process in adaptive questionnaires in LLM-affine areas such as political surveys.

21 January 2026 in Politics and Governance
Verified
Journal Article
Open access
PDF file
FBFynn Bachmann
Fynn Bachmann
DWDaan Van der Weijden
Daan Van der Weijden
CSCristina Sarasua
Cristina Sarasua
ABAbraham Bernstein
Abraham Bernstein
Voting advice applications typically require users to answer questionnaires before receiving party or candidate recommendations. As users answer more questions, the recommendations naturally become more accurate. However, when users do not complete the questionnaire, the certainty of these recommendations is unknown. In this work, we develop and present a measure to quantify this certainty by introducing an algorithm that estimates the candidate recommendation accuracy—the overlap between early and final recommendations—after each question. Through simulations based on existing voter data, we find that our algorithm is more accurate than heuristic estimates. Additionally, it can identify stable recommendations—candidates who are likely to be among the final recommendations—with fewer false positives. Furthermore, we conduct a user experiment investigating different ways of communicating recommendation certainty to users. Our results show that users answer more questions when they see a preview of stable recommendations, but quit the questionnaire earlier when we display an artificially high candidate recommendation accuracy estimate. Moreover, we find that users appreciate the interface’s simplicity over its accuracy. We conclude that displaying personalized stable recommendations can spark curiosity towards voting advice applications while providing a robust estimate of recommendation certainty for users who submit incomplete questionnaires.


12 March 2025 in arXiv
Verified
Preprint
Open access
PDF file
FBFynn Bachmann
Fynn Bachmann
DWDaan van der Weijden
Daan van der Weijden
LHLucien Heitz
Lucien Heitz
CSCristina Sarasua
Cristina Sarasua
ABAbraham Bernstein
Abraham Bernstein
Adaptive questionnaires dynamically select the next question for a survey participant based on their previous answers. Due to digitalisation, they have become a viable alternative to traditional surveys in application areas such as political science. One limitation, however, is their dependency on data to train the model for question selection. Often, such training data (i.e., user interactions) are unavailable a priori. To address this problem, we (i) test whether Large Language Models (LLM) can accurately generate such interaction data and (ii) explore if these synthetic data can be used to pre-train the statistical model of an adaptive political survey. To evaluate this approach, we utilise existing data from the Swiss Voting Advice Application (VAA) Smartvote in two ways: First, we compare the distribution of LLM-generated synthetic data to the real distribution to assess its similarity. Second, we compare the performance of an adaptive questionnaire that is randomly initialised with one pre-trained on synthetic data to assess their suitability for training. We benchmark these results against an "oracle" questionnaire with perfect prior knowledge. We find that an off-the-shelf LLM (GPT-4) accurately generates answers to the Smartvote questionnaire from the perspective of different Swiss parties. Furthermore, we demonstrate that initialising the statistical model with synthetic data can (i) significantly reduce the error in predicting user responses and (ii) increase the candidate recommendation accuracy of the VAA. Our work emphasises the considerable potential of LLMs to create training data to improve the data collection process in adaptive questionnaires in LLM-affine areas such as political surveys.