Social Bias Frames: Reasoning about Social and Power Implications of Language

  title={Social Bias Frames: Reasoning about Social and Power Implications of Language},
  author={Maarten Sap and Saadia Gabriel and Lianhui Qin and Dan Jurafsky and Noah A. Smith and Yejin Choi},
Warning: this paper contains content that may be offensive or upsetting. Language has the power to reinforce stereotypes and project social biases onto others. At the core of the challenge is that it is rarely what is stated explicitly, but rather the implied meanings, that frame people’s judgments about others. For example, given a statement that “we shouldn’t lower our standards to hire more women,” most listeners will infer the implicature intended by the speaker - that “women (candidates… 

Figures and Tables from this paper

CO-STAR: Conceptualisation of Stereotypes for Analysis and Reasoning
The CO-STAR models are limited in their ability to understand more complex and subtly worded stereotypes, and the research motivates future work in developing models with more sophisticated methods for encoding common-sense knowledge.
Understanding and Countering Stereotypes: A Computational Approach to the Stereotype Content Model
This work presents a computational approach to interpreting stereotypes in text through the Stereotype Content Model (SCM), a comprehensive causal theory from social psychology that proposes that stereotypes can be understood along two primary dimensions: warmth and competence.
Argument from Old Man’s View: Assessing Social Bias in Argumentation
This paper trains word embedding models on portal-specific corpora and systematically evaluate their bias using WEAT, an existing metric to measure bias in word embeddings, and investigates causes of bias, suggesting that all tested debate corpora contain unbalanced and biased data.
Computational Modeling of Stereotype Content in Text
Stereotypes are encountered every day, in interpersonal communication as well as in entertainment, news stories, and on social media. In this study, we present a computational method to mine large,
How Do You Speak about Immigrants? Taxonomy and StereoImmigrants Dataset for Identifying Stereotypes about Immigrants
Stereotype is a type of social bias massively present in texts that computational models use. There are stereotypes that present special difficulties because they do not rely on personal attributes.
Uncovering Implicit Gender Bias in Narratives through Commonsense Inference
This work infer and analyze the protagonist’s motivations, attributes, mental states, and implications on others, and uses a commonsense reasoning engine to uncover implicit biases associated with the protagonist in model-generated stories.
French CrowS-Pairs: Extending a challenge dataset for measuring social bias in masked language models to a language other than English
Warning: This paper contains explicit statements of offensive stereotypes which may be upsetting.Much work on biases in natural language processing has addressed biases linked to the social and
Language (Technology) is Power: A Critical Survey of “Bias” in NLP
A greater recognition of the relationships between language and social hierarchies is urged, encouraging researchers and practitioners to articulate their conceptualizations of “bias” and to center work around the lived experiences of members of communities affected by NLP systems.
Social Chemistry 101: Learning to Reason about Social and Moral Norms
A new conceptual formalism to study people's everyday social norms and moral judgments over a rich spectrum of real life situations described in natural language and a model framework, Neural Norm Transformer, learns and generalizes Social-Chem-101 to successfully reason about previously unseen situations, generating relevant (and potentially novel) attribute-aware social rules-of-thumb.
Towards Understanding and Mitigating Social Biases in Language Models
The empirical results and human evaluation demonstrate effectiveness in mitigating bias while retaining crucial contextual information for highfidelity text generation, thereby pushing forward the performance-fairness Pareto frontier.


Echoes of power: language effects and power differences in social interaction
It is shown that in group discussions, power differentials between participants are subtly revealed by how much one individual immediately echoes the linguistic style of the person they are responding to, and an analysis framework based on linguistic coordination is proposed that works consistently across multiple types of power.
Language and Woman's Place
ABSTRACT Our use of language embodies attitudes as well as referential meanings. ‘Woman's language’ has as foundation the attitude that women are marginal to the serious concerns of life, which are
Contextual Affective Analysis: A Case Study of People Portrayals in Online #MeToo Stories
Using a corpus of online media articles about the #MeToo movement, an entity-centric approach that uses contextualized lexicons to examine how people are portrayed in media articles is presented.
Finding Microaggressions in the Wild: A Case for Locating Elusive Phenomena in Social Media Posts
This paper devise a general but nuanced, computationally operationalizable typology of microaggressions based on a small subset of data that they have, and introduces a new, more objective, criterion for annotation and an active-learning based procedure that increases the likelihood of surfacing posts containing microagressions.
Social IQA: Commonsense Reasoning about Social Interactions
It is established that Social IQa, the first large-scale benchmark for commonsense reasoning about social situations, is challenging for existing question-answering models based on pretrained language models, compared to human performance (>20% gap).
Slang and Sociability: In-Group Language Among College Students
Slang is often seen as a lesser form of language, one that is simply not as meaningful or important as its 'regular' counterpart. Connie Eble refutes this notion as she reveals the sources, poetry,
The Risk of Racial Bias in Hate Speech Detection
This work proposes *dialect* and *race priming* as ways to reduce the racial bias in annotation, showing that when annotators are made explicitly aware of an AAE tweet’s dialect they are significantly less likely to label the tweet as offensive.
CONAN - COunter NArratives through Nichesourcing: a Multilingual Dataset of Responses to Fight Online Hate Speech
This paper describes the creation of the first large-scale, multilingual, expert-based dataset of hate-speech/counter-narrative pairs, built with the effort of more than 100 operators from three different NGOs that applied their training and expertise to the task.
Connotation Frames of Power and Agency in Modern Films
This work uses connotation frames of power and agency frames to measure the subtle, but prevalent, gender bias in the portrayal of modern film characters and provide insights that deviate from the well-known Bechdel test.