Problems of Authorship Classification: recognizing the Author Style or a Book

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00023221%3A_____%2F23%3AN0000063" target="_blank" >RIV/00023221:_____/23:N0000063 - isvavai.cz</a>

Výsledek na webu

<a href="https://www.digitalhumanities.org/dhq/vol/17/4/000723/000723.html" target="_blank" >https://www.digitalhumanities.org/dhq/vol/17/4/000723/000723.html</a>

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

Problems of Authorship Classification: recognizing the Author Style or a Book

Popis výsledku v původním jazyce

The presented article proposes that one of the problems regarding authorship attribution tasks is the attribution of a specific book rather than the author. This often leads to overestimated reported performance. This problem is in general connected to the dataset construction and more specifically to the train-test data split. Using a heavily delexicalized and diverse dataset of Czech authors and basic LinearSVC classifiers, we designed a three-step experiment setting to explore book versus author attribution effects. First, the authorship attribution task is performed on a dataset split to train and test data segments across books. Second, the same task is performed on a dataset where individual books are used wholly either for training or testing. Expectedly, this leads to poorer results. In the third step, we do not attribute book segments to authors but to books themselves. This step reveals that there is a general tendency towards attributing to a specific book rather than to different books of the same author. The results indicate that authors who show a higher inner confusion among their works (i.e., the model attributes their works to other works of theirs) tend to perform better in the task of attribution of an unseen book.

Název v anglickém jazyce

Problems of Authorship Classification: recognizing the Author Style or a Book

Popis výsledku anglicky

The presented article proposes that one of the problems regarding authorship attribution tasks is the attribution of a specific book rather than the author. This often leads to overestimated reported performance. This problem is in general connected to the dataset construction and more specifically to the train-test data split. Using a heavily delexicalized and diverse dataset of Czech authors and basic LinearSVC classifiers, we designed a three-step experiment setting to explore book versus author attribution effects. First, the authorship attribution task is performed on a dataset split to train and test data segments across books. Second, the same task is performed on a dataset where individual books are used wholly either for training or testing. Expectedly, this leads to poorer results. In the third step, we do not attribute book segments to authors but to books themselves. This step reveals that there is a general tendency towards attributing to a specific book rather than to different books of the same author. The results indicate that authors who show a higher inner confusion among their works (i.e., the model attributes their works to other works of theirs) tend to perform better in the task of attribution of an unseen book.

Druh

J_ost - Ostatní články v recenzovaných periodicích

CEP obor

—

OECD FORD obor

60500 - Other Humanities and the Arts

Projekt

—

Návaznosti

I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Rok uplatnění

2023

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název periodika

Digital Humanities Quarterly

ISSN

1938-4122

e-ISSN

—

Svazek periodika

2023

Číslo periodika v rámci svazku

17.4

Stát vydavatele periodika

US - Spojené státy americké

Počet stran výsledku

22

Strana od-do

—

Kód UT WoS článku

—

EID výsledku v databázi Scopus

—