What question did this study set out to answer?

The research aims to assess whether large language models can effectively classify poetry from social media posts.

synapse

⌘+K

synapse

⌘+K

May 27, 2026Open Access

Can LLMs Effectively Detect Poetry? Identifying Quality Differences Among Local, Free, and Commercial Models

Key Points

The research aims to assess whether large language models can effectively classify poetry from social media posts.
Analyzed a sample of Facebook posts for formal parameters such as text type and language.
Examined posts in multiple languages including Russian, Ukrainian, and Belarusian.
Tested various models, including local, free, and commercial LLMs.
Local models showed varied effectiveness in detecting poetry compared to commercial models.
Certain content features significantly impacted the classification accuracy.
Model performance differed based on the language of the text analyzed.

Abstract

Information extraction from large text corpora poses particular challenges for social media corpora due to their high diversity in languages, content, and genres. At the same time, social media posts, as relatively manageable and self-contained text fragments, are more advantageous for automated analysis and classification than longer texts. This poster presents an approach for testing the detection of formal parameters such as text type (poetry or not), text language (Russian, Ukrainian, Belarusian, and others), as well as several content features, using a sample of Facebook posts containing published poetry.

Can LLMs Effectively Detect Poetry? Identifying Quality Differences Among Local, Free, and Commercial Models

Key Points

Abstract

Cite This Study

Also Consider

Also Consider