Chatbot-assisted Voting Advice Applications, Political Education with LLMs
How accurately can large language models reproduce political opinions, i.e., how does the generated data differ from real candidates’ answers (Bachmann et al., 2025)?
Which pitfalls must developers consider when implementing chatbots in their Voting Advice Applications?
How can synthetic text generation contribute to political education, and how do users perceive its limitations?
2025
PLOS One
Adaptive political surveys and GPT-4: Tackling the cold start problem with simulated user interactions
Fynn Bachmann, Daan Van Der Weijden, Lucien Heitz, Cristina Sarasua, and 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.
