@inproceedings{van-cranenburgh-ketzan-2021-stylometric,
title = "Stylometric Literariness Classification: the Case of Stephen King",
author = "van Cranenburgh, Andreas and
Ketzan, Erik",
editor = "Degaetano-Ortlieb, Stefania and
Kazantseva, Anna and
Reiter, Nils and
Szpakowicz, Stan",
booktitle = "Proceedings of the 5th Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature",
month = nov,
year = "2021",
address = "Punta Cana, Dominican Republic (online)",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.latechclfl-1.21",
doi = "10.18653/v1/2021.latechclfl-1.21",
pages = "189--197",
abstract = "This paper applies stylometry to quantify the literariness of 73 novels and novellas by American author Stephen King, chosen as an extraordinary case of a writer who has been dubbed both {``}high{''} and {``}low{''} in literariness in critical reception. We operationalize literariness using a measure of stylistic distance (Cosine Delta) based on the 1000 most frequent words in two bespoke comparison corpora used as proxies for literariness: one of popular genre fiction, another of National Book Award-winning authors. We report that a supervised model is highly effective in distinguishing the two categories, with 94.6{\%} macro average in a binary classification. We define two subsets of texts by King{---}{``}high{''} and {``}low{''} literariness works as suggested by critics and ourselves{---}and find that a predictive model does identify King{'}s Dark Tower series and novels such as Dolores Claiborne as among his most {``}literary{''} texts, consistent with critical reception, which has also ascribed postmodern qualities to the Dark Tower novels. Our results demonstrate the efficacy of Cosine Delta-based stylometry in quantifying the literariness of texts, while also highlighting the methodological challenges of literariness, especially in the case of Stephen King. The code and data to reproduce our results are available at \url{https://github.com/andreasvc/kinglit}",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="van-cranenburgh-ketzan-2021-stylometric">
<titleInfo>
<title>Stylometric Literariness Classification: the Case of Stephen King</title>
</titleInfo>
<name type="personal">
<namePart type="given">Andreas</namePart>
<namePart type="family">van Cranenburgh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Erik</namePart>
<namePart type="family">Ketzan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 5th Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature</title>
</titleInfo>
<name type="personal">
<namePart type="given">Stefania</namePart>
<namePart type="family">Degaetano-Ortlieb</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Kazantseva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nils</namePart>
<namePart type="family">Reiter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stan</namePart>
<namePart type="family">Szpakowicz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Punta Cana, Dominican Republic (online)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper applies stylometry to quantify the literariness of 73 novels and novellas by American author Stephen King, chosen as an extraordinary case of a writer who has been dubbed both “high” and “low” in literariness in critical reception. We operationalize literariness using a measure of stylistic distance (Cosine Delta) based on the 1000 most frequent words in two bespoke comparison corpora used as proxies for literariness: one of popular genre fiction, another of National Book Award-winning authors. We report that a supervised model is highly effective in distinguishing the two categories, with 94.6% macro average in a binary classification. We define two subsets of texts by King—“high” and “low” literariness works as suggested by critics and ourselves—and find that a predictive model does identify King’s Dark Tower series and novels such as Dolores Claiborne as among his most “literary” texts, consistent with critical reception, which has also ascribed postmodern qualities to the Dark Tower novels. Our results demonstrate the efficacy of Cosine Delta-based stylometry in quantifying the literariness of texts, while also highlighting the methodological challenges of literariness, especially in the case of Stephen King. The code and data to reproduce our results are available at https://github.com/andreasvc/kinglit</abstract>
<identifier type="citekey">van-cranenburgh-ketzan-2021-stylometric</identifier>
<identifier type="doi">10.18653/v1/2021.latechclfl-1.21</identifier>
<location>
<url>https://aclanthology.org/2021.latechclfl-1.21</url>
</location>
<part>
<date>2021-11</date>
<extent unit="page">
<start>189</start>
<end>197</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Stylometric Literariness Classification: the Case of Stephen King
%A van Cranenburgh, Andreas
%A Ketzan, Erik
%Y Degaetano-Ortlieb, Stefania
%Y Kazantseva, Anna
%Y Reiter, Nils
%Y Szpakowicz, Stan
%S Proceedings of the 5th Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature
%D 2021
%8 November
%I Association for Computational Linguistics
%C Punta Cana, Dominican Republic (online)
%F van-cranenburgh-ketzan-2021-stylometric
%X This paper applies stylometry to quantify the literariness of 73 novels and novellas by American author Stephen King, chosen as an extraordinary case of a writer who has been dubbed both “high” and “low” in literariness in critical reception. We operationalize literariness using a measure of stylistic distance (Cosine Delta) based on the 1000 most frequent words in two bespoke comparison corpora used as proxies for literariness: one of popular genre fiction, another of National Book Award-winning authors. We report that a supervised model is highly effective in distinguishing the two categories, with 94.6% macro average in a binary classification. We define two subsets of texts by King—“high” and “low” literariness works as suggested by critics and ourselves—and find that a predictive model does identify King’s Dark Tower series and novels such as Dolores Claiborne as among his most “literary” texts, consistent with critical reception, which has also ascribed postmodern qualities to the Dark Tower novels. Our results demonstrate the efficacy of Cosine Delta-based stylometry in quantifying the literariness of texts, while also highlighting the methodological challenges of literariness, especially in the case of Stephen King. The code and data to reproduce our results are available at https://github.com/andreasvc/kinglit
%R 10.18653/v1/2021.latechclfl-1.21
%U https://aclanthology.org/2021.latechclfl-1.21
%U https://doi.org/10.18653/v1/2021.latechclfl-1.21
%P 189-197
Markdown (Informal)
[Stylometric Literariness Classification: the Case of Stephen King](https://aclanthology.org/2021.latechclfl-1.21) (van Cranenburgh & Ketzan, LaTeCHCLfL 2021)
ACL
- Andreas van Cranenburgh and Erik Ketzan. 2021. Stylometric Literariness Classification: the Case of Stephen King. In Proceedings of the 5th Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature, pages 189–197, Punta Cana, Dominican Republic (online). Association for Computational Linguistics.