Problem
Research questions and friction points this paper is trying to address.
free-text survey data
interpretable themes
computational analysis
survey research
textual data
In your own words: computationally identifying interpretable themes in free-text survey data
🤖 AI Summary
Free-text survey responses contain rich semantic content yet pose significant challenges for structured analysis, and existing approaches lack systematic methods for extracting interpretable themes. This study proposes a computational framework that integrates natural language processing with topic modeling to automatically identify precise, human-interpretable topics from open-ended responses and enables joint exploratory analysis with quantitative variables. Validation on identity descriptions from 1,004 U.S. participants demonstrates that the approach not only uncovers novel constructs—such as belongingness and identity fluidity—but also explains additional variance in outcomes like health and well-being. The method offers a new pathway for understanding intra-identity heterogeneity, detecting self–other perceptual biases, and informing the design of subsequent structured survey items.
📝 Abstract
Free-text survey responses can provide nuance often missed by structured questions, but remain difficult to statistically analyze. To address this, we introduce In Your Own Words, a computational framework for exploratory analyses of free-text survey data that identifies structured, interpretable themes in free-text responses more precisely than previous computational approaches, facilitating systematic analysis. To illustrate the benefits of this approach, we apply it to a new dataset of free-text descriptions of race, gender, and sexual orientation from 1,004 U.S. participants. The themes our approach learns have three practical applications in survey research. First, the themes can suggest structured questions to add to future surveys by surfacing salient constructs -- such as belonging and identity fluidity -- that existing surveys do not capture. Second, the themes reveal heterogeneity within standardized categories, explaining additional variation in health, well-being, and identity importance. Third, the themes illuminate systematic discordance between self-identified and perceived identities, highlighting mechanisms of misrecognition that existing measures do not reflect. More broadly, our framework can be deployed in a wide range of survey settings to identify interpretable themes from free text, complementing existing qualitative methods.
Innovation
Methods, ideas, or system contributions that make the work stand out.
interpretable themes
free-text survey analysis
computational framework
identity heterogeneity
survey design
🔎 Similar Papers
No similar papers found.
