MoralStrength: Exploiting a moral lexicon and embedding similarity for moral foundations prediction

Oscar Araque (Corresponding Author), Lorenzo Gatti, Kyriaki Kalimeri

Research output: Contribution to journalArticleAcademicpeer-review

2 Downloads (Pure)

Abstract

Moral rhetoric plays a fundamental role in how we perceive and interpret the information we receive, greatly influencing our decision-making process. Especially when it comes to controversial social and political issues, our opinions and attitudes are hardly ever based on evidence alone. The Moral Foundations Dictionary (MFD) was developed to operationalize moral values in the text. In this study, we present MoralStrength, a lexicon of approximately 1,000 lemmas, obtained as an extension of the Moral Foundations Dictionary, based on WordNet synsets. Moreover, for each lemma it provides with a crowdsourced numeric assessment of Moral Valence, indicating the strength with which a lemma is expressing the specific value. We evaluated the predictive potentials of this moral lexicon, defining three utilization approaches of increased complexity, ranging from lemmas’ statistical properties to a deep learning approach of word embeddings based on semantic similarity. Logistic regression models trained on the features extracted from MoralStrength, significantly outperformed the current state-of-the-art, reaching an F1-score of 87.6% over the previous 62.4% (-value ), and an average F1-Score of 86.25% over six different datasets. Such findings pave the way for further research, allowing for an in-depth understanding of moral narratives in text for a wide range of social issues.
Original languageEnglish
JournalKnowledge-based systems
DOIs
Publication statusE-pub ahead of print/First online - 5 Nov 2019

Fingerprint

Glossaries
Logistics
Decision making
Semantics
Prediction
Deep learning

Cite this

@article{079bef2b863a4f05a88317078691602e,
title = "MoralStrength: Exploiting a moral lexicon and embedding similarity for moral foundations prediction",
abstract = "Moral rhetoric plays a fundamental role in how we perceive and interpret the information we receive, greatly influencing our decision-making process. Especially when it comes to controversial social and political issues, our opinions and attitudes are hardly ever based on evidence alone. The Moral Foundations Dictionary (MFD) was developed to operationalize moral values in the text. In this study, we present MoralStrength, a lexicon of approximately 1,000 lemmas, obtained as an extension of the Moral Foundations Dictionary, based on WordNet synsets. Moreover, for each lemma it provides with a crowdsourced numeric assessment of Moral Valence, indicating the strength with which a lemma is expressing the specific value. We evaluated the predictive potentials of this moral lexicon, defining three utilization approaches of increased complexity, ranging from lemmas’ statistical properties to a deep learning approach of word embeddings based on semantic similarity. Logistic regression models trained on the features extracted from MoralStrength, significantly outperformed the current state-of-the-art, reaching an F1-score of 87.6{\%} over the previous 62.4{\%} (-value ), and an average F1-Score of 86.25{\%} over six different datasets. Such findings pave the way for further research, allowing for an in-depth understanding of moral narratives in text for a wide range of social issues.",
author = "Oscar Araque and Lorenzo Gatti and Kyriaki Kalimeri",
year = "2019",
month = "11",
day = "5",
doi = "10.1016/j.knosys.2019.105184",
language = "English",
journal = "Knowledge-based systems",
issn = "0950-7051",
publisher = "Elsevier",

}

MoralStrength: Exploiting a moral lexicon and embedding similarity for moral foundations prediction. / Araque, Oscar (Corresponding Author); Gatti, Lorenzo ; Kalimeri, Kyriaki.

In: Knowledge-based systems, 05.11.2019.

Research output: Contribution to journalArticleAcademicpeer-review

TY - JOUR

T1 - MoralStrength: Exploiting a moral lexicon and embedding similarity for moral foundations prediction

AU - Araque, Oscar

AU - Gatti, Lorenzo

AU - Kalimeri, Kyriaki

PY - 2019/11/5

Y1 - 2019/11/5

N2 - Moral rhetoric plays a fundamental role in how we perceive and interpret the information we receive, greatly influencing our decision-making process. Especially when it comes to controversial social and political issues, our opinions and attitudes are hardly ever based on evidence alone. The Moral Foundations Dictionary (MFD) was developed to operationalize moral values in the text. In this study, we present MoralStrength, a lexicon of approximately 1,000 lemmas, obtained as an extension of the Moral Foundations Dictionary, based on WordNet synsets. Moreover, for each lemma it provides with a crowdsourced numeric assessment of Moral Valence, indicating the strength with which a lemma is expressing the specific value. We evaluated the predictive potentials of this moral lexicon, defining three utilization approaches of increased complexity, ranging from lemmas’ statistical properties to a deep learning approach of word embeddings based on semantic similarity. Logistic regression models trained on the features extracted from MoralStrength, significantly outperformed the current state-of-the-art, reaching an F1-score of 87.6% over the previous 62.4% (-value ), and an average F1-Score of 86.25% over six different datasets. Such findings pave the way for further research, allowing for an in-depth understanding of moral narratives in text for a wide range of social issues.

AB - Moral rhetoric plays a fundamental role in how we perceive and interpret the information we receive, greatly influencing our decision-making process. Especially when it comes to controversial social and political issues, our opinions and attitudes are hardly ever based on evidence alone. The Moral Foundations Dictionary (MFD) was developed to operationalize moral values in the text. In this study, we present MoralStrength, a lexicon of approximately 1,000 lemmas, obtained as an extension of the Moral Foundations Dictionary, based on WordNet synsets. Moreover, for each lemma it provides with a crowdsourced numeric assessment of Moral Valence, indicating the strength with which a lemma is expressing the specific value. We evaluated the predictive potentials of this moral lexicon, defining three utilization approaches of increased complexity, ranging from lemmas’ statistical properties to a deep learning approach of word embeddings based on semantic similarity. Logistic regression models trained on the features extracted from MoralStrength, significantly outperformed the current state-of-the-art, reaching an F1-score of 87.6% over the previous 62.4% (-value ), and an average F1-Score of 86.25% over six different datasets. Such findings pave the way for further research, allowing for an in-depth understanding of moral narratives in text for a wide range of social issues.

UR - https://github.com/oaraque/moral-foundations

U2 - 10.1016/j.knosys.2019.105184

DO - 10.1016/j.knosys.2019.105184

M3 - Article

JO - Knowledge-based systems

JF - Knowledge-based systems

SN - 0950-7051

ER -