@inproceedings{cao-etal-2024-moral,
title = "The Moral Foundations {W}eibo Corpus",
author = "Cao, Renjie and
Hu, Miaoyan and
Wei, Jiahan and
Ihnaini, Baha",
editor = "Peled-Cohen, Lotem and
Calderon, Nitay and
Lissak, Shir and
Reichart, Roi",
booktitle = "Proceedings of the 1st Workshop on NLP for Science (NLP4Science)",
month = nov,
year = "2024",
address = "Miami, FL, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.nlp4science-1.13",
pages = "155--165",
abstract = "Moral sentiments expressed in natural language significantly influence both online and offline environments, shaping behavioral styles and interaction patterns, including social media self-presentation, cyberbullying, adherence to social norms, and ethical decision-making. To effectively measure moral sentiments in natural language processing texts, it is crucial to utilize large, annotated datasets that provide nuanced understanding for accurate analysis and model training. However, existing corpora, while valuable, often face linguistic limitations. To address this gap in the Chinese language domain, we introduce the Moral Foundation Weibo Corpus. This corpus consists of 25,671 Chinese comments on Weibo, encompassing six diverse topic areas. Each comment is manually annotated by at least three systematically trained annotators based on ten moral categories derived from a grounded theory of morality. To assess annotator reliability, we present the kappa test results, a gold standard for measuring consistency. Additionally, we apply several the latest large language models to supplement the manual annotations, conducting analytical experiments to compare their performance and report baseline results for moral sentiment classification.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="cao-etal-2024-moral">
<titleInfo>
<title>The Moral Foundations Weibo Corpus</title>
</titleInfo>
<name type="personal">
<namePart type="given">Renjie</namePart>
<namePart type="family">Cao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Miaoyan</namePart>
<namePart type="family">Hu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiahan</namePart>
<namePart type="family">Wei</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Baha</namePart>
<namePart type="family">Ihnaini</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 1st Workshop on NLP for Science (NLP4Science)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lotem</namePart>
<namePart type="family">Peled-Cohen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nitay</namePart>
<namePart type="family">Calderon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shir</namePart>
<namePart type="family">Lissak</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Roi</namePart>
<namePart type="family">Reichart</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Miami, FL, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Moral sentiments expressed in natural language significantly influence both online and offline environments, shaping behavioral styles and interaction patterns, including social media self-presentation, cyberbullying, adherence to social norms, and ethical decision-making. To effectively measure moral sentiments in natural language processing texts, it is crucial to utilize large, annotated datasets that provide nuanced understanding for accurate analysis and model training. However, existing corpora, while valuable, often face linguistic limitations. To address this gap in the Chinese language domain, we introduce the Moral Foundation Weibo Corpus. This corpus consists of 25,671 Chinese comments on Weibo, encompassing six diverse topic areas. Each comment is manually annotated by at least three systematically trained annotators based on ten moral categories derived from a grounded theory of morality. To assess annotator reliability, we present the kappa test results, a gold standard for measuring consistency. Additionally, we apply several the latest large language models to supplement the manual annotations, conducting analytical experiments to compare their performance and report baseline results for moral sentiment classification.</abstract>
<identifier type="citekey">cao-etal-2024-moral</identifier>
<location>
<url>https://aclanthology.org/2024.nlp4science-1.13</url>
</location>
<part>
<date>2024-11</date>
<extent unit="page">
<start>155</start>
<end>165</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T The Moral Foundations Weibo Corpus
%A Cao, Renjie
%A Hu, Miaoyan
%A Wei, Jiahan
%A Ihnaini, Baha
%Y Peled-Cohen, Lotem
%Y Calderon, Nitay
%Y Lissak, Shir
%Y Reichart, Roi
%S Proceedings of the 1st Workshop on NLP for Science (NLP4Science)
%D 2024
%8 November
%I Association for Computational Linguistics
%C Miami, FL, USA
%F cao-etal-2024-moral
%X Moral sentiments expressed in natural language significantly influence both online and offline environments, shaping behavioral styles and interaction patterns, including social media self-presentation, cyberbullying, adherence to social norms, and ethical decision-making. To effectively measure moral sentiments in natural language processing texts, it is crucial to utilize large, annotated datasets that provide nuanced understanding for accurate analysis and model training. However, existing corpora, while valuable, often face linguistic limitations. To address this gap in the Chinese language domain, we introduce the Moral Foundation Weibo Corpus. This corpus consists of 25,671 Chinese comments on Weibo, encompassing six diverse topic areas. Each comment is manually annotated by at least three systematically trained annotators based on ten moral categories derived from a grounded theory of morality. To assess annotator reliability, we present the kappa test results, a gold standard for measuring consistency. Additionally, we apply several the latest large language models to supplement the manual annotations, conducting analytical experiments to compare their performance and report baseline results for moral sentiment classification.
%U https://aclanthology.org/2024.nlp4science-1.13
%P 155-165
Markdown (Informal)
[The Moral Foundations Weibo Corpus](https://aclanthology.org/2024.nlp4science-1.13) (Cao et al., NLP4Science 2024)
ACL
- Renjie Cao, Miaoyan Hu, Jiahan Wei, and Baha Ihnaini. 2024. The Moral Foundations Weibo Corpus. In Proceedings of the 1st Workshop on NLP for Science (NLP4Science), pages 155–165, Miami, FL, USA. Association for Computational Linguistics.