In their new article, “Question Form Matters: Examining Trust in Government through Open and Closed Survey Items”, Jana Bernhard-Harrer and Katharina Pfaff explore how the way we ask survey questions can significantly shape the answers we receive.

While previous research has examined differences between open-ended and closed-ended survey responses, our understanding remains fragmented — especially given the growing interest in open-ended questions made possible by advances in automated text analysis.

The authors investigate how computational text analysis methods — particularly large language models — can efficiently analyse open-ended responses, yielding promising results for sentiment detection and actor identification, though topic classification remains more challenging.

They then systematically compare open-ended and closed-ended responses on trust in the Austrian coalition government, assessing how different formats influence the expression of political trust. The results show significant discrepancies between trust levels indicated in closed-ended questions and those expressed in open-ended answers, with paired t-tests revealing statistically significant differences.

These findings underline that question format influences how respondents express their views, raising important considerations about the usefulness and validity of trust measures. Open-ended questions capture nuanced perspectives often missed by closed-ended formats, offering unique value for survey design.

Read the full article here: https://academic.oup.com/jssam/advance-article/doi/10.1093/jssam/smaf014/8223439#528681307

Cite the article:
Bernhard-Harrer, J., & Pfaff, K. (2025). Question form matters: Examining trust in government through open and closed survey items. Journal of Survey Statistics and Methodology. Advance online publication. https://doi.org/10.1093/jssam/smaf014