Sibling-texts keyword analysis: exploring topic and register keywords

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11210%2F25%3A10508091" target="_blank" >RIV/00216208:11210/25:10508091 - isvavai.cz</a>

Výsledek na webu

<a href="https://verso.is.cuni.cz/pub/verso.fpl?fname=obd_publikace_handle&handle=U5ysKb.edD" target="_blank" >https://verso.is.cuni.cz/pub/verso.fpl?fname=obd_publikace_handle&handle=U5ysKb.edD</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1093/llc/fqaf037" target="_blank" >10.1093/llc/fqaf037</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Sibling-texts keyword analysis: exploring topic and register keywords

Popis výsledku v původním jazyce

This article introduces a novel method for refining approaches to distant reading by proposing a procedure that categorizes prominent units (keywords) into two types: those pertinent to the topic and those associated with the genre/register of a text. This differentiation holds significant potential for more accurate modeling of topics and further applications in various domains of digital humanities. For example, register-related keywords may assist in various stylometric tasks, such as functional understanding of text groups (formed through clustering) that exhibit common stylistic traits, thus differentiating themselves from other groups or clusters within the discourse under scrutiny. In the initial step of the procedure, a set of texts with similar genre and register characteristics is identified; we term them &apos;sibling texts&apos;, and their similarity is determined using a model derived from multidimensional analysis. The next step involves conducting multiple parallel keyword analyses on these sibling texts and comparing them for keyword overlaps which mark the register relatedness. The test study on a corpus of Czech parliamentary speeches (Parlcorp) underscores the method&apos;s ability to distinguish register-related and topic-related keywords, even in highly homogeneous corpora. The register-related keywords proved to be analytically very useful in substantiating the interpretation of parliamentary subregisters and advancing the understanding of the types of activities (administrative and procedural, deliberating and debating, and government policies) involved in parliamentary discourse.

Název v anglickém jazyce

Sibling-texts keyword analysis: exploring topic and register keywords

Popis výsledku anglicky

This article introduces a novel method for refining approaches to distant reading by proposing a procedure that categorizes prominent units (keywords) into two types: those pertinent to the topic and those associated with the genre/register of a text. This differentiation holds significant potential for more accurate modeling of topics and further applications in various domains of digital humanities. For example, register-related keywords may assist in various stylometric tasks, such as functional understanding of text groups (formed through clustering) that exhibit common stylistic traits, thus differentiating themselves from other groups or clusters within the discourse under scrutiny. In the initial step of the procedure, a set of texts with similar genre and register characteristics is identified; we term them &apos;sibling texts&apos;, and their similarity is determined using a model derived from multidimensional analysis. The next step involves conducting multiple parallel keyword analyses on these sibling texts and comparing them for keyword overlaps which mark the register relatedness. The test study on a corpus of Czech parliamentary speeches (Parlcorp) underscores the method&apos;s ability to distinguish register-related and topic-related keywords, even in highly homogeneous corpora. The register-related keywords proved to be analytically very useful in substantiating the interpretation of parliamentary subregisters and advancing the understanding of the types of activities (administrative and procedural, deliberating and debating, and government policies) involved in parliamentary discourse.

Druh

J_imp - Článek v periodiku v databázi Web of Science

CEP obor

—

OECD FORD obor

60203 - Linguistics

Projekt

<a href="/cs/project/EH22_008%2F0004595" target="_blank" >EH22_008/0004595: Za hranice bezpečnosti: role konfliktu v posilování odolnosti</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)<br>I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Rok uplatnění

2025

Kód důvěrnosti údajů

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

Název periodika

Digital Scholarship in the Humanities

ISSN

2055-7671

e-ISSN

2055-768X

Svazek periodika

40

Číslo periodika v rámci svazku

3

Stát vydavatele periodika

US - Spojené státy americké

Počet stran výsledku

17

Strana od-do

762-778

Kód UT WoS článku

001489511400001

EID výsledku v databázi Scopus

2-s2.0-105015176616