Đã lưu trong:
| Tác giả chính: | |
|---|---|
| Định dạng: | Recurso digital |
| Ngôn ngữ: | |
| Được phát hành: |
Zenodo
2026
|
| Truy cập trực tuyến: | https://doi.org/10.5281/zenodo.18879146 |
| Các nhãn: |
Thêm thẻ
Không có thẻ, Là người đầu tiên thẻ bản ghi này!
|
Mục lục:
- <div> <div>This Zenodo record contains a de-identified results replication package for a subject-specific (single-case) longitudinal study of personality-related language in a predominantly professional email archive spanning 2008–2024. The analysis uses theory-guided LLM-based coding (prompted GPT-3.5) and a teacher–student pipeline (GPT-4.1 agentic teacher distilled into compact multilingual transformer students) to produce email-level classifications that are aggregated into monthly indices and analyzed with HAC-robust regressions against pre-specified contextual covariates.</div> <br> <div>The package includes:</div> <br> <div>- Processed, de-identified email-level classification outputs (no raw email text, no subjects, no addresses; dates reduced to month start for aggregation)</div> <div>- Derived monthly indices, coverage summaries, and regression-ready covariate tables</div> <div>- Regression outputs (coefficient tables, fit summaries) and figure-generation scripts</div> <div>- Precomputed figures matching the manuscript (only)</div> <br> <div>Not included:</div> <br> <div>- Raw emails or verbatim email text</div> <div>- Email subjects, sender/recipient fields, or other direct identifiers</div> <div>- Full prompt dumps or long implementation logs</div> <br> <div>To reproduce key results, unzip all ZIP files into the same directory (they unpack directly into `Data/`, `Results/`, and a small set of top-level scripts), then run `uv sync` followed by `uv run python generate_manuscript_figures.py` (see `Replication_package/replication_README.md`).</div> </div>