@inproceedings{nikolova-navarretta-2024-evaluating-word,
title = "Evaluating Word Expansion for Multilingual Sentiment Analysis of Parliamentary Speech",
author = "Nikolova, Yana and
Navarretta, Costanza",
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.581",
pages = "6557--6563",
abstract = "This paper replicates and evaluates the word expansion (WE) method for sentiment lexicon generation from Rheault et al. (2016), applying it to two novel corpora of parliamentary speech from Denmark and Bulgaria. GloVe embeddings and vector similarity are leveraged to expand synonym seed lists with domain-specific terms from the speech corpora. The resulting Danish and Bulgarian lexica are compared to other multilingual lexica by analyzing a gold standard of speech excerpts annotated for sentiment. WE correlates best with hand-coded annotations for Danish, while a machine-translated Lexicoder dictionary does best for Bulgarian. WE performance is also found to be very sensitive to processing and scoring techniques, though this is also an issue with the other lexica. Overall, automatic lexicon translation best balances computational complexity and accuracy across both languages, but robust language-agnosticism remains elusive. Theoretical and practical problems of WE are discussed.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="nikolova-navarretta-2024-evaluating-word">
<titleInfo>
<title>Evaluating Word Expansion for Multilingual Sentiment Analysis of Parliamentary Speech</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yana</namePart>
<namePart type="family">Nikolova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Costanza</namePart>
<namePart type="family">Navarretta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper replicates and evaluates the word expansion (WE) method for sentiment lexicon generation from Rheault et al. (2016), applying it to two novel corpora of parliamentary speech from Denmark and Bulgaria. GloVe embeddings and vector similarity are leveraged to expand synonym seed lists with domain-specific terms from the speech corpora. The resulting Danish and Bulgarian lexica are compared to other multilingual lexica by analyzing a gold standard of speech excerpts annotated for sentiment. WE correlates best with hand-coded annotations for Danish, while a machine-translated Lexicoder dictionary does best for Bulgarian. WE performance is also found to be very sensitive to processing and scoring techniques, though this is also an issue with the other lexica. Overall, automatic lexicon translation best balances computational complexity and accuracy across both languages, but robust language-agnosticism remains elusive. Theoretical and practical problems of WE are discussed.</abstract>
<identifier type="citekey">nikolova-navarretta-2024-evaluating-word</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.581</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>6557</start>
<end>6563</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Evaluating Word Expansion for Multilingual Sentiment Analysis of Parliamentary Speech
%A Nikolova, Yana
%A Navarretta, Costanza
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F nikolova-navarretta-2024-evaluating-word
%X This paper replicates and evaluates the word expansion (WE) method for sentiment lexicon generation from Rheault et al. (2016), applying it to two novel corpora of parliamentary speech from Denmark and Bulgaria. GloVe embeddings and vector similarity are leveraged to expand synonym seed lists with domain-specific terms from the speech corpora. The resulting Danish and Bulgarian lexica are compared to other multilingual lexica by analyzing a gold standard of speech excerpts annotated for sentiment. WE correlates best with hand-coded annotations for Danish, while a machine-translated Lexicoder dictionary does best for Bulgarian. WE performance is also found to be very sensitive to processing and scoring techniques, though this is also an issue with the other lexica. Overall, automatic lexicon translation best balances computational complexity and accuracy across both languages, but robust language-agnosticism remains elusive. Theoretical and practical problems of WE are discussed.
%U https://aclanthology.org/2024.lrec-main.581
%P 6557-6563
Markdown (Informal)
[Evaluating Word Expansion for Multilingual Sentiment Analysis of Parliamentary Speech](https://aclanthology.org/2024.lrec-main.581) (Nikolova & Navarretta, LREC-COLING 2024)
ACL