acR: Content Analysis in R: Integrated Qualitative (LLMs) and Quantitative Pipeline
- 7 August 2026
- dataset
- Published by The R Foundation
Abstract
Provides an integrated pipeline for content analysis combining qualitative coding assisted by large language models (LLMs) with classical quantitative text analysis. Includes modules for pre-processing (tokenization, stopwords for Brazilian Portuguese), descriptive statistics, keyness, co-occurrence networks, word clouds (including comparative and X-ray variants), sentiment analysis via OpLexicon, Latent Dirichlet Allocation (LDA), inter-coder reliability metrics (Krippendorff, Gwet), and modern visualizations based on ggplot2. Special focus on Brazilian corpora and political-institutional codebooks. Inspired by Maerz and Benoit (2025) .Keywords
This publication has 3 references indexed in Scilit:
- ellmer: Chat with Large Language Models2025
- ChatGPT outperforms crowd workers for text-annotation tasksProceedings of the National Academy of Sciences of the United States of America, 2023
- quanteda: An R package for the quantitative analysis of textual dataJournal of Open Source Software, 2018