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	11,302	1: 1,354, 2: 1,258, 3: 959, 4: 1,070, 5: 944, 6: 879, 7: 930, 8: 1,473, 9: 1,139, 10: 1,296	240	3162.278	0.053	2.577	2.681	0.104	2.940	ready
Including Books 4 and 8	Function Words	11,302	1: 1,354, 2: 1,258, 3: 959, 4: 1,070, 5: 944, 6: 879, 7: 930, 8: 1,473, 9: 1,139, 10: 1,296	160	3162.278	0.039	2.605	2.681	0.077	2.962	ready
Including Books 4 and 8	Character 4-Grams	11,302	1: 1,354, 2: 1,258, 3: 959, 4: 1,070, 5: 944, 6: 879, 7: 930, 8: 1,473, 9: 1,139, 10: 1,296	220	3162.278	0.056	2.571	2.681	0.110	2.936	ready
Excluding Books 4 and 8	Morphosyntax	8,759	1: 1,354, 2: 1,258, 3: 959, 5: 944, 6: 879, 7: 930, 9: 1,139, 10: 1,296	240	3162.278	0.065	2.714	2.850	0.136	3.120	ready
Excluding Books 4 and 8	Function Words	8,759	1: 1,354, 2: 1,258, 3: 959, 5: 944, 6: 879, 7: 930, 9: 1,139, 10: 1,296	160	3162.278	0.046	2.756	2.850	0.095	3.152	ready
Excluding Books 4 and 8	Character 4-Grams	8,759	1: 1,354, 2: 1,258, 3: 959, 5: 944, 6: 879, 7: 930, 9: 1,139, 10: 1,296	220	3162.278	0.070	2.714	2.850	0.137	3.112	ready

Predictive Stylometric Features

Variant	Feature family	Largest standardized coefficients
Including Books 4 and 8	Morphosyntax	later_books: `Head>child PROPN>DET` (0.140) earlier_books: `Feature VerbForm=Part` (-0.114) earlier_books: `Head direction advcl:left` (-0.091) earlier_books: `Head>child VERB>PROPN` (-0.088) earlier_books: `Head>child NOUN>DET` (-0.086) later_books: `Feature PronType=Prs` (0.084) earlier_books: `Feature Case=Acc` (-0.079) earlier_books: `Feature Voice=Act` (-0.078)
Including Books 4 and 8	Function Words	later_books: `Function form/UPOS οἱ:DET` (0.108) earlier_books: `Function form/UPOS οἱ:PRON` (-0.099) earlier_books: `Function DepRel advcl` (-0.098) earlier_books: `Function DepRel obl` (-0.097) earlier_books: `Function UPOS PRON` (-0.094) earlier_books: `Function word γὰρ` (-0.089) later_books: `Function form/UPOS τε:CCONJ` (0.086) later_books: `Function word ἡ` (0.084)
Including Books 4 and 8	Character 4-Grams	earlier_books: `char 4-gram αὶ τ` (-0.128) earlier_books: `char 4-gram ἀθην` (-0.117) later_books: `char 4-gram ἐκ` (0.111) later_books: `char 4-gram αὶ ἐ` (0.100) later_books: `char 4-gram δὴ` (0.093) later_books: `char 4-gram τὰ` (0.089) later_books: `char 4-gram τῆι` (0.088) earlier_books: `char 4-gram ν ἀρ` (-0.085)
Excluding Books 4 and 8	Morphosyntax	later_books: `Head>child PROPN>DET` (0.148) earlier_books: `Head>child VERB>PROPN` (-0.112) earlier_books: `Feature Number=Sing` (-0.107) earlier_books: `Feature VerbForm=Part` (-0.107) later_books: `Feature Number=Plur` (0.105) earlier_books: `Head direction advcl:left` (-0.102) later_books: `DepRel/UPOS obj:NOUN` (0.094) earlier_books: `Feature Case=Acc` (-0.094)
Excluding Books 4 and 8	Function Words	later_books: `Function form/UPOS οἱ:DET` (0.148) earlier_books: `Function form/UPOS οἱ:PRON` (-0.130) earlier_books: `Function DepRel obl` (-0.111) later_books: `Function form/UPOS τε:CCONJ` (0.107) earlier_books: `Function DepRel advcl` (-0.103) later_books: `Function word τε` (0.097) earlier_books: `Function word γὰρ` (-0.089) later_books: `Function word ἡ` (0.086)
Excluding Books 4 and 8	Character 4-Grams	later_books: `char 4-gram ντο` (0.149) earlier_books: `char 4-gram θηνα` (-0.134) earlier_books: `char 4-gram ν ἀρ` (-0.130) later_books: `char 4-gram τὰ` (0.121) earlier_books: `char 4-gram αὶ τ` (-0.120) later_books: `char 4-gram ἐκ` (0.119) earlier_books: `char 4-gram καλο` (-0.109) later_books: `char 4-gram τε` (0.109)