A Hierarchical Error Framework for Reliable Automated Coding in Communication Research: Applications to Health and Political Communication

Replication package (v2) for the Hierarchical Error Correction (HEC) Framework manuscript submitted to Communication Methods and Measures. This package supports two usage paths: - Offline (preferred for reviewers): use pre-computed results/cached outputs if present - Online: re-run experiments with API access Version 2 enhancements: - Offline-safe helper scripts (quick_check.py, make_tables.py, make_figures.py) - Structured output directories (tables/, figures_out/, cached_outputs/) - CITATION.cff with DOI - Improved README with one-click commands The package includes: - Complete source code for all four experiments (medical transcription, legal classification, political bias detection, legal reasoning) - Configuration files - Validation tests - Analysis and visualization tools - MIT License For detailed usage instructions, see README.md inside the package.