Analysis outputs and model variants
The current paper-facing analysis uses the active three-bucket tags, then restricts the model to mythic vs. historical sentences.
The active tag batch currently has no book 4 or book 8 sentences, so the all-books and excluding-books-4-and-8 variants use the same sample for now.
| Vocabulary | Book Scope | Rhetoric Markers | Sample | Features | Accuracy | Page |
|---|---|---|---|---|---|---|
| Lemma | Excluding 4 and 8 | Included | 2,393 | 1,000 | 0.693 | Open |
| Lemma | Excluding 4 and 8 | Removed | 2,393 | 1,000 | 0.696 | Open |
| Lemma | All books | Included | 2,393 | 1,000 | 0.693 | Open |
| Lemma | All books | Removed | 2,393 | 1,000 | 0.696 | Open |
| Surface | Excluding 4 and 8 | Included | 2,393 | 1,000 | 0.686 | Open |
| Surface | Excluding 4 and 8 | Removed | 2,393 | 1,000 | 0.684 | Open |
| Surface | All books | Included | 2,393 | 1,000 | 0.686 | Open |
| Surface | All books | Removed | 2,393 | 1,000 | 0.684 | Open |
Greek predictors of length residuals, plus the dual view of English terms found in longer or shorter-than-expected passages.
Open Translation Length AnalysisGeographic map, place-pair distances, and proper-noun co-occurrence network pages.
Open Place and Network PagesMythic/historical subgraphs, bridge nouns, book-level drift, and place-person/deity networks.
Open Network Analyses