English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Obtaining stakeholders' diverse experiences and opinions about current policyin a timely manner is crucial for policymakers to identify strengths and gapsin resource allocation, thereby supporting effective policy design andimplementation. However, manually coding even moderately sized interview textsor open-ended survey responses from stakeholders can often be labor-intensiveand time-consuming. This study explores the integration of Large LanguageModels (LLMs)--like GPT-4--with human expertise to enhance text analysis ofstakeholder interviews regarding K-12 education policy within one U.S. state.Employing a mixed-methods approach, human experts developed a codebook andcoding processes as informed by domain knowledge and unsupervised topicmodeling results. They then designed prompts to guide GPT-4 analysis anditeratively evaluate different prompts' performances. This combinedhuman-computer method enabled nuanced thematic and sentiment analysis. Resultsreveal that while GPT-4 thematic coding aligned with human coding by 77.89% atspecific themes, expanding to broader themes increased congruence to 96.02%,surpassing traditional Natural Language Processing (NLP) methods by over 25%.Additionally, GPT-4 is more closely matched to expert sentiment analysis thanlexicon-based methods. Findings from quantitative measures and qualitativereviews underscore the complementary roles of human domain expertise andautomated analysis as LLMs offer new perspectives and coding consistency. Thehuman-computer interactive approach enhances efficiency, validity, andinterpretability of educational policy research.

From Voices to Validity: Leveraging Large Language Models (LLMs) for Textual Analysis of Policy Stakeholder Interviews