@inproceedings{navarretta-haltrup-hansen-2020-identifying,
title = "Identifying Parties in Manifestos and Parliament Speeches",
author = "Navarretta, Costanza and
Haltrup Hansen, Dorte",
editor = "Fi{\v{s}}er, Darja and
Eskevich, Maria and
de Jong, Franciska",
booktitle = "Proceedings of the Second ParlaCLARIN Workshop",
month = may,
year = "2020",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2020.parlaclarin-1.10",
pages = "51--57",
abstract = "This paper addresses differences in the word use of two left-winged and two right-winged Danish parties, and how these differences reflecting some of the basic stances of the parties can be used to automatically identify the party of politicians from their speeches. In the first study, the most frequent and characteristic lemmas in the manifestos of the political parties are analysed. The analysis shows that the most frequently occurring lemmas in the manifestos reflect either the ideology or the position of the parties towards specific subjects, confirming for Danish preceding studies of English and German manifestos. Successively, we scaled our analysis applying machine learning on different language models built on the transcribed speeches by members of the same parties in the Parliament (Hansards) in order to determine to what extent it is possible to predict the party of the politicians from the speeches. The speeches used are a subset of the Danish Parliament corpus 2009{--}2017. The best models resulted in a weighted F1-score of 0.57. These results are significantly better than the results obtained by the majority classifier (F1-score = 0.11) and by chance results (0.25) and show that building language models over the speeches used by politicians can be used to identify the politicians{'} party even if they debate about the same subjects and thus often use the same terminology in many cases. In the future, we will include the subject of the speeches in the prediction experiments",
language = "English",
ISBN = "979-10-95546-47-4",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="navarretta-haltrup-hansen-2020-identifying">
<titleInfo>
<title>Identifying Parties in Manifestos and Parliament Speeches</title>
</titleInfo>
<name type="personal">
<namePart type="given">Costanza</namePart>
<namePart type="family">Navarretta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dorte</namePart>
<namePart type="family">Haltrup Hansen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">English</languageTerm>
<languageTerm type="code" authority="iso639-2b">eng</languageTerm>
</language>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Second ParlaCLARIN Workshop</title>
</titleInfo>
<name type="personal">
<namePart type="given">Darja</namePart>
<namePart type="family">Fišer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Eskevich</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Franciska</namePart>
<namePart type="family">de Jong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-10-95546-47-4</identifier>
</relatedItem>
<abstract>This paper addresses differences in the word use of two left-winged and two right-winged Danish parties, and how these differences reflecting some of the basic stances of the parties can be used to automatically identify the party of politicians from their speeches. In the first study, the most frequent and characteristic lemmas in the manifestos of the political parties are analysed. The analysis shows that the most frequently occurring lemmas in the manifestos reflect either the ideology or the position of the parties towards specific subjects, confirming for Danish preceding studies of English and German manifestos. Successively, we scaled our analysis applying machine learning on different language models built on the transcribed speeches by members of the same parties in the Parliament (Hansards) in order to determine to what extent it is possible to predict the party of the politicians from the speeches. The speeches used are a subset of the Danish Parliament corpus 2009–2017. The best models resulted in a weighted F1-score of 0.57. These results are significantly better than the results obtained by the majority classifier (F1-score = 0.11) and by chance results (0.25) and show that building language models over the speeches used by politicians can be used to identify the politicians’ party even if they debate about the same subjects and thus often use the same terminology in many cases. In the future, we will include the subject of the speeches in the prediction experiments</abstract>
<identifier type="citekey">navarretta-haltrup-hansen-2020-identifying</identifier>
<location>
<url>https://aclanthology.org/2020.parlaclarin-1.10</url>
</location>
<part>
<date>2020-05</date>
<extent unit="page">
<start>51</start>
<end>57</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Identifying Parties in Manifestos and Parliament Speeches
%A Navarretta, Costanza
%A Haltrup Hansen, Dorte
%Y Fišer, Darja
%Y Eskevich, Maria
%Y de Jong, Franciska
%S Proceedings of the Second ParlaCLARIN Workshop
%D 2020
%8 May
%I European Language Resources Association
%C Marseille, France
%@ 979-10-95546-47-4
%G English
%F navarretta-haltrup-hansen-2020-identifying
%X This paper addresses differences in the word use of two left-winged and two right-winged Danish parties, and how these differences reflecting some of the basic stances of the parties can be used to automatically identify the party of politicians from their speeches. In the first study, the most frequent and characteristic lemmas in the manifestos of the political parties are analysed. The analysis shows that the most frequently occurring lemmas in the manifestos reflect either the ideology or the position of the parties towards specific subjects, confirming for Danish preceding studies of English and German manifestos. Successively, we scaled our analysis applying machine learning on different language models built on the transcribed speeches by members of the same parties in the Parliament (Hansards) in order to determine to what extent it is possible to predict the party of the politicians from the speeches. The speeches used are a subset of the Danish Parliament corpus 2009–2017. The best models resulted in a weighted F1-score of 0.57. These results are significantly better than the results obtained by the majority classifier (F1-score = 0.11) and by chance results (0.25) and show that building language models over the speeches used by politicians can be used to identify the politicians’ party even if they debate about the same subjects and thus often use the same terminology in many cases. In the future, we will include the subject of the speeches in the prediction experiments
%U https://aclanthology.org/2020.parlaclarin-1.10
%P 51-57
Markdown (Informal)
[Identifying Parties in Manifestos and Parliament Speeches](https://aclanthology.org/2020.parlaclarin-1.10) (Navarretta & Haltrup Hansen, ParlaCLARIN 2020)
ACL