Pausanias Analysis

Book-number regression from stylometric features

Can Stylometric Features Predict Book Number?

This page uses Ridge regression, not classification, to predict the numeric book number of each grammar-parsed sentence. Chance is the per-fold training-set mean book number.

These models use only sentences with current LLM grammar-token rows, so the sample is smaller than the full annotation corpus.
Strict three-way and mythic-vs-historical tasks drop rare both/mixed rows; one-vs-rest tasks use the available mythic/historical flags where present.
Character 4-grams are included as a traditional baseline; morphosyntax is the primary non-lexical stylometric family.

Open feature trend diagnostics | Download regression metrics CSV | Download regression features CSV

Regression Metrics

Variant	Features	n	Book counts	Features	Alpha	R2	MAE	Chance MAE	MAE improvement	RMSE	Status
Including Books 4 and 8	Morphosyntax	2,920	1: 343, 2: 318, 3: 256, 4: 281, 5: 255, 6: 223, 7: 246, 8: 402, 9: 278, 10: 318	240	3162.278	0.031	2.580	2.650	0.070	2.943	ready
Including Books 4 and 8	Function Words	2,920	1: 343, 2: 318, 3: 256, 4: 281, 5: 255, 6: 223, 7: 246, 8: 402, 9: 278, 10: 318	160	3162.278	0.010	2.618	2.650	0.032	2.974	ready
Including Books 4 and 8	Character 4-Grams	2,920	1: 343, 2: 318, 3: 256, 4: 281, 5: 255, 6: 223, 7: 246, 8: 402, 9: 278, 10: 318	220	3162.278	0.036	2.574	2.650	0.076	2.936	ready
Excluding Books 4 and 8	Morphosyntax	2,237	1: 343, 2: 318, 3: 256, 5: 255, 6: 223, 7: 246, 9: 278, 10: 318	240	3162.278	0.049	2.709	2.809	0.100	3.115	ready
Excluding Books 4 and 8	Function Words	2,237	1: 343, 2: 318, 3: 256, 5: 255, 6: 223, 7: 246, 9: 278, 10: 318	160	3162.278	0.027	2.750	2.809	0.060	3.151	ready
Excluding Books 4 and 8	Character 4-Grams	2,237	1: 343, 2: 318, 3: 256, 5: 255, 6: 223, 7: 246, 9: 278, 10: 318	220	3162.278	0.041	2.732	2.809	0.077	3.129	ready

Predictive Stylometric Features

Variant	Feature family	Largest standardized coefficients
Including Books 4 and 8	Morphosyntax	earlier_books: `Feature Voice=Act` (-0.080) earlier_books: `Feature VerbForm=Part` (-0.075) earlier_books: `Head direction advcl:left` (-0.070) later_books: `Head>child PROPN>DET` (0.064) later_books: `Head>child PROPN>CCONJ` (0.062) earlier_books: `DepRel/UPOS obj:PROPN` (-0.059) later_books: `DepRel/UPOS nmod:PRON` (0.058) later_books: `Feature Voice=Mid` (0.057)
Including Books 4 and 8	Function Words	later_books: `Function form/UPOS ἡ:DET` (0.060) later_books: `Function word ἡ` (0.060) later_books: `Function form/UPOS οἱ:DET` (0.058) earlier_books: `Function form/UPOS τοὺσ:DET` (-0.055) earlier_books: `Function word τοὺσ` (-0.055) earlier_books: `Function UPOS PRON` (-0.055) later_books: `Function word τῆι` (0.052) later_books: `Function form/UPOS τῆι:DET` (0.052)
Including Books 4 and 8	Character 4-Grams	earlier_books: `char 4-gram αὶ τ` (-0.087) earlier_books: `char 4-gram οισ` (-0.086) later_books: `char 4-gram δὴ` (0.083) later_books: `char 4-gram ντο` (0.078) later_books: `char 4-gram αὶ ἐ` (0.078) earlier_books: `char 4-gram ἀθην` (-0.076) earlier_books: `char 4-gram ἀθη` (-0.069) later_books: `char 4-gram τὸ` (0.062)
Excluding Books 4 and 8	Morphosyntax	earlier_books: `Feature Voice=Act` (-0.078) earlier_books: `Feature VerbForm=Part` (-0.070) later_books: `Feature Voice=Mid` (0.067) earlier_books: `Head direction advcl:left` (-0.065) earlier_books: `Feature Person=1` (-0.064) earlier_books: `Feature Number=Sing` (-0.063) later_books: `Head>child PROPN>DET` (0.062) earlier_books: `Head>child PRON>ADP` (-0.061)
Excluding Books 4 and 8	Function Words	later_books: `Function form/UPOS οἱ:DET` (0.075) earlier_books: `Function DepRel obl` (-0.072) later_books: `Function form/UPOS τε:CCONJ` (0.068) later_books: `Function form/UPOS ἡ:DET` (0.062) later_books: `Function word ἡ` (0.062) earlier_books: `Function DepRel obj` (-0.060) later_books: `Function word τε` (0.056) earlier_books: `Function UPOS PRON` (-0.056)
Excluding Books 4 and 8	Character 4-Grams	earlier_books: `char 4-gram ν ἀρ` (-0.090) earlier_books: `char 4-gram οισ` (-0.078) later_books: `char 4-gram αὶ ἐ` (0.076) later_books: `char 4-gram δὴ` (0.076) earlier_books: `char 4-gram θηνα` (-0.075) earlier_books: `char 4-gram αὶ τ` (-0.075) earlier_books: `char 4-gram ντοσ` (-0.069) earlier_books: `char 4-gram α κα` (-0.068)