Machine learning canonicity in Dutch novels 1800-2000

Andreas van Cranenburgh

Machine learning canonicity in Dutch novels 1800-2000

Computational Linguistics (CL)

Onderzoeksoutput › Academic

Samenvatting

In a previous post, we introduced a dataset of Dutch novels with textual features and metadata. In this post we explore the dataset with the aim of answering the question to what extent canonicity can be predicted using textual features. We first explore syntactic characteristics, and then train a classifier on lexical frequencies.

Originele taal-2	English
Mijlpalentype toekennen	Research blog post
Outputmedia	lab.kb.nl
Uitgever	Koninklijke Bibliotheek
Status	Published - 24-jan.-2022

Toegang tot document

https://lab.kb.nl/about-us/blog/machine-learning-canonicity-dutch-novels-1800-2000Licentie: Unspecified

Handle.net

Permanente koppeling

1 Abstract

DBNL als goudmijn voor de digitale neerlandistiek
Keltjens, R., van Cranenburgh, A., van der Eecken, P., van Erp, M. & Leemans, I., aug.-2022.
Onderzoeksoutput › Academic

Bestand

Textual features and metadata for DBNL novels 1800-2000
van Cranenburgh, A. (Creator), Veldhoen, S. (Creator) & de Gruijter, M. (Creator), Koninklijke Bibliotheek, 31-jan.-2022
DOI: 10.5281/zenodo.5786254, https://lab.kb.nl/dataset/dutch-novels-1800-2000
Dataset

Onder de loep
van Cranenburgh, A.
01/03/2022
1 Mediabijdrage
Pers / media: Expert Comment › Popular

Citeer dit

@misc{43df22ffa8b3473c91b764ac697153d6,

title = "Machine learning canonicity in Dutch novels 1800-2000",

abstract = "In a previous post, we introduced a dataset of Dutch novels with textual features and metadata. In this post we explore the dataset with the aim of answering the question to what extent canonicity can be predicted using textual features. We first explore syntactic characteristics, and then train a classifier on lexical frequencies.",

author = "{van Cranenburgh}, Andreas",

year = "2022",

month = jan,

day = "24",

language = "English",

publisher = "Koninklijke Bibliotheek",

type = "Other",

}

TY - GEN

T1 - Machine learning canonicity in Dutch novels 1800-2000

AU - van Cranenburgh, Andreas

PY - 2022/1/24

Y1 - 2022/1/24

N2 - In a previous post, we introduced a dataset of Dutch novels with textual features and metadata. In this post we explore the dataset with the aim of answering the question to what extent canonicity can be predicted using textual features. We first explore syntactic characteristics, and then train a classifier on lexical frequencies.

AB - In a previous post, we introduced a dataset of Dutch novels with textual features and metadata. In this post we explore the dataset with the aim of answering the question to what extent canonicity can be predicted using textual features. We first explore syntactic characteristics, and then train a classifier on lexical frequencies.

M3 - Other contribution

PB - Koninklijke Bibliotheek

ER -

Machine learning canonicity in Dutch novels 1800-2000

Samenvatting

Toegang tot document

Handle.net

Vingerafdruk

Onderzoekersoutput

DBNL als goudmijn voor de digitale neerlandistiek

Datasets

Textual features and metadata for DBNL novels 1800-2000

Pers/Media

Onder de loep

Citeer dit