A Pertinence Score for Political Discourse Analysis: The Case of 2018 Colombian Elections

Juan Carlos Garcia; Damián Fernández Pedemonte; Carmen Vaca; Maria Baquerizo-Neira

doi:10.1145/3689213

A Pertinence Score for Political Discourse Analysis: The Case of 2018 Colombian Elections

Juan Carlos Garcia^*, Damián Fernández Pedemonte, Carmen Vaca, Maria Baquerizo-Neira

^*Corresponding author for this work

Research output: Contribution to journal › Article › peer-review

1 Scopus citations

Abstract

This study proposes a quantitative method to assess the pertinence of political language on national issues, addressing the complexity of analyzing political discourse and its relevance to citizens' concerns. Using word embeddings and linguistic models trained on Wikipedia, a "pertinence score"was developed to measure the relevance of political discourse in contexts such as the economy and health. The method was applied to the 2018 Colombian presidential election, revealing significant differences in thematic pertinence between candidates. Survey validation confirmed the correlation between automatic and human scores, highlighting the model's ability to discriminate ideological positions through lexical analysis.

Original language	English
Article number	34
Journal	Digital Government: Research and Practice
Volume	5
Issue number	3
DOIs	https://doi.org/10.1145/3689213
State	Published - 8 Oct 2024
Externally published	Yes

Bibliographical note

Publisher Copyright:
© 2024 Copyright held by the owner/author(s).

Keywords

Colombia
elections
neural language model
Political discourse

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1145/3689213

Cite this

@article{72b21ed57415474d88a5e0bf5b17fd90,

title = "A Pertinence Score for Political Discourse Analysis: The Case of 2018 Colombian Elections",

abstract = "This study proposes a quantitative method to assess the pertinence of political language on national issues, addressing the complexity of analyzing political discourse and its relevance to citizens' concerns. Using word embeddings and linguistic models trained on Wikipedia, a {"}pertinence score{"}was developed to measure the relevance of political discourse in contexts such as the economy and health. The method was applied to the 2018 Colombian presidential election, revealing significant differences in thematic pertinence between candidates. Survey validation confirmed the correlation between automatic and human scores, highlighting the model's ability to discriminate ideological positions through lexical analysis.",

keywords = "Colombia, elections, neural language model, Political discourse",

author = "Garcia, \{Juan Carlos\} and \{Fern{\'a}ndez Pedemonte\}, Dami{\'a}n and Carmen Vaca and Maria Baquerizo-Neira",

note = "Publisher Copyright: {\textcopyright} 2024 Copyright held by the owner/author(s).",

year = "2024",

month = oct,

day = "8",

doi = "10.1145/3689213",

language = "English",

volume = "5",

journal = "Digital Government: Research and Practice",

issn = "2639-0175",

publisher = "Association for Computing Machinery (ACM)",

number = "3",

}

TY - JOUR

T1 - A Pertinence Score for Political Discourse Analysis

T2 - The Case of 2018 Colombian Elections

AU - Garcia, Juan Carlos

AU - Fernández Pedemonte, Damián

AU - Vaca, Carmen

AU - Baquerizo-Neira, Maria

PY - 2024/10/8

Y1 - 2024/10/8

N2 - This study proposes a quantitative method to assess the pertinence of political language on national issues, addressing the complexity of analyzing political discourse and its relevance to citizens' concerns. Using word embeddings and linguistic models trained on Wikipedia, a "pertinence score"was developed to measure the relevance of political discourse in contexts such as the economy and health. The method was applied to the 2018 Colombian presidential election, revealing significant differences in thematic pertinence between candidates. Survey validation confirmed the correlation between automatic and human scores, highlighting the model's ability to discriminate ideological positions through lexical analysis.

AB - This study proposes a quantitative method to assess the pertinence of political language on national issues, addressing the complexity of analyzing political discourse and its relevance to citizens' concerns. Using word embeddings and linguistic models trained on Wikipedia, a "pertinence score"was developed to measure the relevance of political discourse in contexts such as the economy and health. The method was applied to the 2018 Colombian presidential election, revealing significant differences in thematic pertinence between candidates. Survey validation confirmed the correlation between automatic and human scores, highlighting the model's ability to discriminate ideological positions through lexical analysis.

KW - Colombia

KW - elections

KW - neural language model

KW - Political discourse

UR - http://www.scopus.com/inward/record.url?scp=85207076004&partnerID=8YFLogxK

U2 - 10.1145/3689213

DO - 10.1145/3689213

M3 - Article

AN - SCOPUS:85207076004

SN - 2639-0175

VL - 5

JO - Digital Government: Research and Practice

JF - Digital Government: Research and Practice

IS - 3

M1 - 34

ER -

A Pertinence Score for Political Discourse Analysis: The Case of 2018 Colombian Elections

Abstract

Bibliographical note

Keywords

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this