Measuring Moral Rhetoric in Text Sagi, Eyal; Dehghani, Morteza
Social science computer review,
04/2014, Volume:
32, Issue:
2
Journal Article
Peer reviewed
In this paper we present a computational text analysis technique for measuring the moral loading of concepts as they are used in a corpus. This method is especially useful for the study of online ...corpora as it allows for the rapid analysis of moral rhetoric in texts such as blogs and tweets as events unfold. We use latent semantic analysis to compute the semantic similarity between concepts and moral keywords taken from the “Moral foundation Dictionary”. This measure of semantic similarity represents the loading of these concepts on the five moral dimensions identified by moral foundation theory. We demonstrate the efficacy of this method using three different concepts and corpora.
Understanding motivations underlying acts of hatred are essential for developing strategies to prevent such extreme behavioral expressions of prejudice (EBEPs) against marginalized groups. In this ...work, we investigate the motivations underlying EBEPs as a function of moral values. Specifically, we propose EBEPs may often be best understood as morally motivated behaviors grounded in people's moral values and perceptions of moral violations. As evidence, we report five studies that integrate spatial modeling and experimental methods to investigate the relationship between moral values and EBEPs. Our results, from these U.S. based studies, suggest that moral values oriented around group preservation are predictive of the county-level prevalence of hate groups and associated with the belief that extreme behavioral expressions of prejudice against marginalized groups are justified. Additional analyses suggest that the association between group-based moral values and EBEPs against outgroups can be partly explained by the belief that these groups have done something morally wrong.
Theory-driven text analysis has made extensive use of psychological concept dictionaries, leading to a wide range of important results. These dictionaries have generally been applied through word ...count methods which have proven to be both simple and effective. In this paper, we introduce Distributed Dictionary Representations (DDR), a method that applies psychological dictionaries using semantic similarity rather than word counts. This allows for the measurement of the similarity between dictionaries and spans of text ranging from complete documents to individual words. We show how DDR enables dictionary authors to place greater emphasis on construct validity without sacrificing linguistic coverage. We further demonstrate the benefits of DDR on two real-world tasks and finally conduct an extensive study of the interaction between dictionary size and task performance. These studies allow us to examine how DDR and word count methods complement one another as tools for applying concept dictionaries and where each is best applied. Finally, we provide references to tools and resources to make this method both available and accessible to a broad psychological audience.
It is widely accepted that language requires context in order to function as communication between speakers and listeners. As listeners, we make use of background knowledge — about the speaker, about ...entities and concepts, about previous utterances — in order to infer the speaker’s intended meaning. But even if there is consensus that these sources of information are a necessary component of linguistic communication, it is another matter entirely to provide a thorough, quantitative accounting for context’s interaction with language. When does context matter? What kinds of context matter in which kinds of domains? The empirical investigation of these questions is inhibited by a number of factors: the challenge of quantifying language, the boundless combinations of domains and types of context to be measured, and the challenge of selecting and applying a given construct to natural language data. In response to these factors, we introduce and demonstrate a methodological framework for testing the importance of contextual information in inferring speaker intentions from text. We apply Long Short-term Memory (LSTM) networks, a standard for representing language in its natural, sequential state, and conduct a set of experiments for predicting the persuasive intentions of speakers in political debates using different combinations of text and background information about the speaker. We show, in our modeling and discussion, that the proposed framework is suitable for empirically evaluating the manner and magnitude of context’s relevance for any number of domains and constructs.
Do appeals to moral values promote charitable donation during natural disasters? Using Distributed Dictionary Representation, we analyze tweets posted during Hurricane Sandy to explore associations ...between moral values and charitable donation sentiment. We then derive hypotheses from the observed associations and test these hypotheses across a series of preregistered experiments that investigate the effects of moral framing on perceived donation motivation (Studies 2 & 3), hypothetical donation (Study 4), and real donation behavior (Study 5). Overall, we find consistent positive associations between moral care and loyalty framing with donation sentiment and donation motivation. However, in contrast with people’s perceptions, we also find that moral frames may not actually have reliable effects on charitable donation, as measured by hypothetical indications of donation and real donation behavior. Overall, this work demonstrates that theoretically constrained, exploratory social media analyses can be used to generate viable hypotheses, but also that such approaches should be paired with rigorous controlled experiments.
Centuries' worth of cultural stories suggest that self-sacrifice may be a cornerstone of our moral concepts, yet this notion is largely absent from recent theories in moral psychology. For instance, ...in the footbridge version of the well-known trolley car problem the only way to save five people from a runaway trolley is to push a single man on the tracks. It is explicitly specified that the bystander cannot sacrifice himself because his weight is insufficient to stop the trolley. But imagine if this were not the case. Would people rather sacrifice themselves than push another? In Study 1, we find that people approve of self-sacrifice more than directly harming another person to achieve the same outcome. In Studies 2 and 3, we demonstrate that the effect is not broadly about sensitivity to self-cost, instead there is something unique about sacrificing the self. Important theoretical implications about agent-relativity and the role of causality in moral judgments are discussed.
Research has shown that accounting for moral sentiment in natural language can yield insight into a variety of on- and off-line phenomena such as message diffusion, protest dynamics, and social ...distancing. However, measuring moral sentiment in natural language is challenging, and the difficulty of this task is exacerbated by the limited availability of annotated data. To address this issue, we introduce the Moral Foundations Twitter Corpus, a collection of 35,108 tweets that have been curated from seven distinct domains of discourse and hand annotated by at least three trained annotators for 10 categories of moral sentiment. To facilitate investigations of annotator response dynamics, we also provide psychological and demographic metadata for each annotator. Finally, we report moral sentiment classification baselines for this corpus using a range of popular methodologies.
Social stereotypes negatively impact individuals’ judgments about different groups and may have a critical role in understanding language directed toward marginalized groups. Here, we assess the role ...of social stereotypes in the automated detection of hate speech in the English language by examining the impact of social stereotypes on annotation behaviors, annotated datasets, and hate speech classifiers. Specifically, we first investigate the impact of novice annotators’ stereotypes on their hate-speech-annotation behavior. Then, we examine the effect of normative stereotypes in language on the aggregated annotators’ judgments in a large annotated corpus. Finally, we demonstrate how normative stereotypes embedded in language resources are associated with systematic prediction errors in a hate-speech classifier. The results demonstrate that hate-speech classifiers reflect social stereotypes against marginalized groups, which can perpetuate social inequalities when propagated at scale. This framework, combining social-psychological and computational-linguistic methods, provides insights into sources of bias in hate-speech moderation, informing ongoing debates regarding machine learning fairness.
Online radicalization is among the most vexing challenges the world faces today. Here, we demonstrate that homogeneity in moral concerns results in increased levels of radical intentions. In Study 1, ...we find that in Gab—a right-wing extremist network—the degree of moral convergence within a cluster predicts the number of hate-speech messages members post. In Study 2, we replicate this observation in another extremist network, Incels. In Studies 3 to 5 (N = 1,431), we demonstrate that experimentally leading people to believe that others in their hypothetical or real group share their moral views increases their radical intentions as well as willingness to fight and die for the group. Our findings highlight the role of moral convergence in radicalization, emphasizing the need for diversity of moral worldviews within social networks.
We present the Gab Hate Corpus (GHC), consisting of 27,665 posts from the social network service gab.com, each annotated for the presence of “hate-based rhetoric” by a minimum of three annotators. ...Posts were labeled according to a coding typology derived from a synthesis of hate speech definitions across legal precedent, previous hate speech coding typologies, and definitions from psychology and sociology, comprising hierarchical labels indicating dehumanizing and violent speech as well as indicators of targeted groups and rhetorical framing. We provide inter-annotator agreement statistics and perform a classification analysis in order to validate the corpus and establish performance baselines. The GHC complements existing hate speech datasets in its theoretical grounding and by providing a large, representative sample of richly annotated social media posts.
PDF
