Moral Foundations Twitter Corpus: A Collection of 35k Tweets Annotated for Moral Sentiment

Hoover, Joe; Portillo-Wightman, Gwenyth; Yeh, Leigh; Havaldar, Shreya; Davani, Aida Mostafazadeh; Lin, Ying; Kennedy, Brendan; Atari, Mohammad; Kamel, Zahra; Mendlen, Madelyn; Moreno, Gabriela; Park, Christina; Chang, Tingyee E.; Chin, Jenna H.; Leong, Christian; Leung, Jun Yen; Mirinjian, Arineh; Dehghani, Morteza

doi:10.1177/1948550619876629

Cited by 99 publications

(92 citation statements)

References 38 publications

(78 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…For the evaluation of our models, we employed the Moral Foundation Twitter Corpus (MFTC) [14]. MFTC is the most extensive available corpus containing 35,108 tweets and annotations, specifically collected to assess the moral values from user-generated content.…”

Section: Data Collection and Preprocessingmentioning

confidence: 99%

“…All data were collected downloading the original tweets following the Twitter IDs provided in the MFTC [14]. Since users often delete their tweets, we only managed to recover a portion of the original datasets.…”

Section: Data Collection and Preprocessingmentioning

confidence: 99%

“…Next we present the performance of the models on Baltimore Protest, All Lives Matter, Black Lives Matter, Davidson and 2016 Presidential Election datasets in Tables 4,5,6,7,8,9,and 10,respectively. According to the previous discussion, we employ the under-sampling technique in all cases, always reporting the SOTA, as described in Hoover et al [14] 11 . Carefully comparing the experimental results, we first note that unigrams provide a reasonably good baseline for all datasets.…”

Section: Evaluation Of Moralstrength Lexiconmentioning

confidence: 99%

“…We believe that exploratory analysis will be useful for the ever-increasing studies on moral foundations since it presents a variety of approaches on how the moral lexicon we propose can be employed for the prediction of moral narratives from a text. Table 7: F1-Score of the proposed methods using under-sampling over ALM [14]. C/H: Care/Harm, F/C: Fairness/Cheating, L/B: Loyalty/Betrayal, A/S: Authority/Subversion, P/D: Purity/Degradation, NM: Non-moral, Avg.…”

Section: Evaluation Of Moralstrength Lexiconmentioning

confidence: 99%

“…The suggested framework includes three models of increasing complexity; two of them are based on straightforward feature extraction from lemma frequencies and statistical properties, while the third one is based on embedding representation of semantic similarity. We thoroughly evaluate the proposed framework employing the Moral Foundations Twitter Corpus (MFTC) [14]. The MFTC corpus is a collection of seven Twitter dataset previously employed in studies related to moral detection from text.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

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

Araque

Gatti

Kalimeri

2020

Knowledge-Based Systems

View full text Add to dashboard Cite

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 Word-Net 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% (p-value< 0.01), 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.

show abstract

Section: Data Collection and Preprocessingmentioning

confidence: 99%

Section: Data Collection and Preprocessingmentioning

confidence: 99%

Section: Evaluation Of Moralstrength Lexiconmentioning

confidence: 99%

Section: Evaluation Of Moralstrength Lexiconmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

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

Araque

Gatti

Kalimeri

2020

Knowledge-Based Systems

View full text Add to dashboard Cite

show abstract

A tale of two hashtags: An examination of moral content of pro‐ and anti‐government tweets in Turkey

Bayrak

Alper

2021

Euro J Social Psych

View full text Add to dashboard Cite

Amidst the 2018 presidential campaign, Turkish President Recep Tayyip Erdogan said "If one day our nation says tamam 1 (enough), then we will step aside" in his parliamentary speech. After Erdoğan's speech, there was a burst of comments on social media, especially on Twitter (Pierpoint et al., 2018). Opponents of Erdogan, including the members of parliament from opposition parties, reacted to Erdogan's words by tweeting using the "#tamam" hashtag, which was used to advocate that it is enough and it is time for Erdogan to step aside. As a reaction to this, Erdogan's supporters, including some of the ministers and deputies, responded by starting the hashtag "#devam" (which means "continue") to show their support for Erdogan's government. These two hashtags were used almost 2 million times in one day and they both ended up on Twitter's worldwide trending topic list (Pierpoint et al., 2018). In this study, the pro-and antigovernment tweets with the "#tamam" and "#devam" hashtags were analyzed in terms of their moral content. We examined the content of 186,554 tweets (86,554 pro-and 100,000 anti-government) within the framework of the Moral Foundations Theory (MFT;

show abstract

The science behind “values”: Applying moral foundations theory to strategic foresight

Mills¹,

Wilner

2022

Futures & Foresight Science

View full text Add to dashboard Cite

“Values” play an oversized role in strategic foresight: they help define scanning frameworks, direct scanning efforts, inform change driver and scenario development, and underpin change within various systems and domains (e.g., politics, society, etc.). And yet, values are largely understudied within foresight. They are rarely defined consistently or explored with reference to a theoretical model of how values emerge or evolve. Rather, values are researched using dissimilar methods depending on the foresight research at hand, which can lead to gaps in analysis and inconsistency between foresight projects. Moral Foundations Theory (MFT), a social psychological theory that identifies common human moral values, offers a solution. MFT describes six moral values or “foundations”—care, fairness, loyalty, authority, sanctity, and liberty—each explained through the evolutionary development of humanity and detectable across cultures. Within foresight, MFT can be applied to understand and identify shifts in the influence of different values, which can result in more novel and unexpected conclusions. With these potential benefits available, we propose adopting and adapting MFT for use within the foresight to improve the way it approaches, identifies, and utilizes values. Our article unpacks MFT into its core tenets and illustrates how it can be used to inform scanning, change driver development, and scenario construction.

show abstract

Moral Foundations Twitter Corpus: A Collection of 35k Tweets Annotated for Moral Sentiment

Cited by 99 publications

References 38 publications

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

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

A tale of two hashtags: An examination of moral content of pro‐ and anti‐government tweets in Turkey

The science behind “values”: Applying moral foundations theory to strategic foresight

Contact Info

Product

Resources

About