acR
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) <https://quallmer.github.io/quallmer/>.
This page was built for software: acR
