chatRater: Rating and Evaluating Texts Using Large Language Models

Generates ratings and psycholinguistic metrics for textual stimuli using large language models. It enables users to evaluate idioms and other language materials by combining context, prompts, and stimulus inputs. It supports multiple LLM APIs (such as 'OpenAI', 'DeepSeek', 'Anthropic', 'Cohere', 'Google PaLM', and 'Ollama') by allowing users to switch models with a single parameter. In addition to generating numeric ratings, 'chatRater' provides functions for obtaining detailed psycholinguistic metrics including word frequency (with optional corpus input), lexical coverage (with customizable vocabulary size and test basis), Zipf metric, Levenshtein distance, and semantic transparency.

Version: 1.1.0
Imports: openai, httr, jsonlite
Suggests: testthat
Published: 2025-03-03
DOI: 10.32614/CRAN.package.chatRater
Author: Shiyang Zheng [aut, cre]
Maintainer: Shiyang Zheng <Shiyang.Zheng at nottingham.ac.uk>
License: MIT + file LICENSE
NeedsCompilation: no
Materials: README
CRAN checks: chatRater results

Documentation:

Reference manual: chatRater.pdf

Downloads:

Package source: chatRater_1.1.0.tar.gz
Windows binaries: r-devel: chatRater_1.0.0.zip, r-release: chatRater_1.1.0.zip, r-oldrel: chatRater_1.0.0.zip
macOS binaries: r-devel (arm64): chatRater_1.1.0.tgz, r-release (arm64): chatRater_1.1.0.tgz, r-oldrel (arm64): chatRater_1.1.0.tgz, r-devel (x86_64): chatRater_1.1.0.tgz, r-release (x86_64): chatRater_1.1.0.tgz, r-oldrel (x86_64): chatRater_1.1.0.tgz
Old sources: chatRater archive

Linking:

Please use the canonical form https://CRAN.R-project.org/package=chatRater to link to this page.