Chatbot Voting Advice Applications inform but seldom sway young unaligned voters
Bibliographic record
Abstract
Voting Advice Applications (VAAs) are interactive tools that communicate information about elections, yet their effectiveness in enhancing political knowledge and participation remains understudied. Moreover, traditional VAAs may disproportionately attract politically engaged users with already well-formed ideological views, limiting their potential to inform a broader and less engaged electorate. This paper introduces a "VAA Bot" that employs large language models (LLMs) and retrieval-augmented generation to deliver balanced, personalized information drawn from official party platforms and public documents. We evaluate the VAA Bot's impact across three experimental studies aimed at young politically unaffiliated adults. The findings provide evidence that the VAA Bot improves knowledge of party stances on issues of great importance to each user. However, the VAA Bot produces weak effects on downstream outcomes such as vote preferences and party evaluations among respondents whose primary issue position aligns closely with one of the parties. These findings contribute to ongoing debates about the role of political information in shaping behavior and clarify both the promise and the limitations of LLM-based tools for civic learning.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.002 | 0.013 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.021 | 0.010 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".