@inproceedings{sidarenka-stede-2016-generating,
title = "Generating Sentiment Lexicons for {G}erman {T}witter",
author = "Sidarenka, Uladzimir and
Stede, Manfred",
editor = "Nissim, Malvina and
Patti, Viviana and
Plank, Barbara",
booktitle = "Proceedings of the Workshop on Computational Modeling of People{'}s Opinions, Personality, and Emotions in Social Media ({PEOPLES})",
month = dec,
year = "2016",
address = "Osaka, Japan",
publisher = "The COLING 2016 Organizing Committee",
url = "https://aclanthology.org/W16-4309",
pages = "80--90",
abstract = "Despite a substantial progress made in developing new sentiment lexicon generation (SLG) methods for English, the task of transferring these approaches to other languages and domains in a sound way still remains open. In this paper, we contribute to the solution of this problem by systematically comparing semi-automatic translations of common English polarity lists with the results of the original automatic SLG algorithms, which were applied directly to German data. We evaluate these lexicons on a corpus of 7,992 manually annotated tweets. In addition to that, we also collate the results of dictionary- and corpus-based SLG methods in order to find out which of these paradigms is better suited for the inherently noisy domain of social media. Our experiments show that semi-automatic translations notably outperform automatic systems (reaching a macro-averaged F1-score of 0.589), and that dictionary-based techniques produce much better polarity lists as compared to corpus-based approaches (whose best F1-scores run up to 0.479 and 0.419 respectively) even for the non-standard Twitter genre.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sidarenka-stede-2016-generating">
<titleInfo>
<title>Generating Sentiment Lexicons for German Twitter</title>
</titleInfo>
<name type="personal">
<namePart type="given">Uladzimir</namePart>
<namePart type="family">Sidarenka</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Manfred</namePart>
<namePart type="family">Stede</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2016-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Workshop on Computational Modeling of People’s Opinions, Personality, and Emotions in Social Media (PEOPLES)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Malvina</namePart>
<namePart type="family">Nissim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Viviana</namePart>
<namePart type="family">Patti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Barbara</namePart>
<namePart type="family">Plank</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>The COLING 2016 Organizing Committee</publisher>
<place>
<placeTerm type="text">Osaka, Japan</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Despite a substantial progress made in developing new sentiment lexicon generation (SLG) methods for English, the task of transferring these approaches to other languages and domains in a sound way still remains open. In this paper, we contribute to the solution of this problem by systematically comparing semi-automatic translations of common English polarity lists with the results of the original automatic SLG algorithms, which were applied directly to German data. We evaluate these lexicons on a corpus of 7,992 manually annotated tweets. In addition to that, we also collate the results of dictionary- and corpus-based SLG methods in order to find out which of these paradigms is better suited for the inherently noisy domain of social media. Our experiments show that semi-automatic translations notably outperform automatic systems (reaching a macro-averaged F1-score of 0.589), and that dictionary-based techniques produce much better polarity lists as compared to corpus-based approaches (whose best F1-scores run up to 0.479 and 0.419 respectively) even for the non-standard Twitter genre.</abstract>
<identifier type="citekey">sidarenka-stede-2016-generating</identifier>
<location>
<url>https://aclanthology.org/W16-4309</url>
</location>
<part>
<date>2016-12</date>
<extent unit="page">
<start>80</start>
<end>90</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Generating Sentiment Lexicons for German Twitter
%A Sidarenka, Uladzimir
%A Stede, Manfred
%Y Nissim, Malvina
%Y Patti, Viviana
%Y Plank, Barbara
%S Proceedings of the Workshop on Computational Modeling of People’s Opinions, Personality, and Emotions in Social Media (PEOPLES)
%D 2016
%8 December
%I The COLING 2016 Organizing Committee
%C Osaka, Japan
%F sidarenka-stede-2016-generating
%X Despite a substantial progress made in developing new sentiment lexicon generation (SLG) methods for English, the task of transferring these approaches to other languages and domains in a sound way still remains open. In this paper, we contribute to the solution of this problem by systematically comparing semi-automatic translations of common English polarity lists with the results of the original automatic SLG algorithms, which were applied directly to German data. We evaluate these lexicons on a corpus of 7,992 manually annotated tweets. In addition to that, we also collate the results of dictionary- and corpus-based SLG methods in order to find out which of these paradigms is better suited for the inherently noisy domain of social media. Our experiments show that semi-automatic translations notably outperform automatic systems (reaching a macro-averaged F1-score of 0.589), and that dictionary-based techniques produce much better polarity lists as compared to corpus-based approaches (whose best F1-scores run up to 0.479 and 0.419 respectively) even for the non-standard Twitter genre.
%U https://aclanthology.org/W16-4309
%P 80-90
Markdown (Informal)
[Generating Sentiment Lexicons for German Twitter](https://aclanthology.org/W16-4309) (Sidarenka & Stede, PEOPLES 2016)
ACL
- Uladzimir Sidarenka and Manfred Stede. 2016. Generating Sentiment Lexicons for German Twitter. In Proceedings of the Workshop on Computational Modeling of People’s Opinions, Personality, and Emotions in Social Media (PEOPLES), pages 80–90, Osaka, Japan. The COLING 2016 Organizing Committee.