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/

Zendy Plus

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

Zendy Tools

Zendy Open

Recent advances in large language models (LLMs) like GPT-3.5 and GPT-4promise automation with better results and less programming, opening up newopportunities for text analysis in political science. In this study, weevaluate LLMs on three original coding tasks involving typical complexitiesencountered in political science settings: a non-English language, legal andpolitical jargon, and complex labels based on abstract constructs. Along thepaper, we propose a practical workflow to optimize the choice of the model andthe prompt. We find that the best prompting strategy consists of providing theLLMs with a detailed codebook, as the one provided to human coders. In thissetting, an LLM can be as good as or possibly better than a human annotatorwhile being much faster, considerably cheaper, and much easier to scale tolarge amounts of text. We also provide a comparison of GPT and popularopen-source LLMs, discussing the trade-offs in the model's choice. Our softwareallows LLMs to be easily used as annotators and is publicly available:https://github.com/lorelupo/pappa.

Towards Human-Level Text Coding with LLMs: The Case of Fatherhood Roles in Public Policy Documents