An official website of the United States government
Current studies of bias in NLP rely mainly on identifying (unwanted or negative) bias towards a specific demographic group. While this has led to progress recognizing and mitigating negative bias, and having a clear notion of the targeted group is necessary, it is not always practical. In this work we extrapolate to a broader notion of bias, rooted in social science and psychology literature. We move towards predicting interpersonal group relationship (IGR) - modeling the relationship between the speaker and the target in an utterance - using fine-grained interpersonal emotions as an anchor. We build and release a dataset of English tweets by US Congress members annotated for interpersonal emotion - the first of its kind, and ‘found supervision’ for IGR labels; our analyses show that subtle emotional signals are indicative of different biases. While humans can perform better than chance at identifying IGR given an utterance, we show that neural models perform much better; furthermore, a shared encoding between IGR and interpersonal perceived emotion enabled performance gains in both tasks.
more »
« less
Counterfactual Probing for the Influence of Affect and Specificity on Intergroup Bias
While existing work on studying bias in NLP focuses on negative or pejorative language use, Govindarajan et al. (2023) offer a revised framing of bias in terms of intergroup social context, and its effects on language behavior. In this paper, we investigate if two pragmatic features (specificity and affect) systematically vary in different intergroup contexts — thus connecting this new framing of bias to language output. Preliminary analysis finds modest correlations between specificity and affect of tweets with supervised intergroup relationship (IGR) labels. Counterfactual probing further reveals that while neural models finetuned for predicting IGR reliably use affect in classification, the model’s usage of specificity is inconclusive.
more »
« less
- PAR ID:
- 10432266
- Date Published:
- Journal Name:
- Findings of the Association for Computational Linguistics: ACL 2023
- Page Range / eLocation ID:
- 12853–12862
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
The variations between in-group and out-group speech (intergroup bias) are subtle and could underlie many social phenomena like stereotype perpetuation and implicit bias. In this paper, we model intergroup bias as a tagging task on English sports comments from forums dedicated to fandom for NFL teams. We curate a dataset of over 6 million game-time comments from opposing perspectives (the teams in the game), each comment grounded in a non-linguistic description of the events that precipitated these comments (live win probabilities for each team). Expert and crowd annotations justify modeling the bias through tagging of implicit and explicit referring expressions and reveal the rich, contextual understanding of language and the world required for this task. For large-scale analysis of intergroup variation, we use LLMs for automated tagging, and discover that LLMs occasionally perform better when prompted with linguistic descriptions of the win probability at the time of the comment, rather than numerical probability. Further, large-scale tagging of comments using LLMs uncovers linear variations in the form of referent across win probabilities that distinguish in-group and out-group utterances.more » « less
-
Decades of research on how to improve intergroup relations have primarily examined ways to change prejudiced attitudes. However, this focus on negative intergroup attitudes has yielded few effective solutions. Because intergroup relations are shaped by behavior during intergroup interactions, it is necessary to identify constructs that have a strong causal impact on intergroup behavior change. In this article, I will discuss evidence showing that intergroup attitude change is neither a sufficient nor necessary cause for intergroup behavior change. Empirical research suggests that intergroup attitudes are difficult to change and have a limited effect on intergroup behavior. I also distinguish between constructs that primarily affect intergroup attitude change (e.g., counterstereotypical exemplars, evaluative conditioning) and constructs that primarily affect intergroup behavior change (e.g., social norms, self-efficacy). Further, suggestions for future research will also be provided to advance understanding of the various psychological constructs that influence intergroup behavior change, which will help us develop effective methods of improving intergroup relations.more » « less
-
While exposure to diverse viewpoints may reduce polarization, it can also have a backfire effect and exacerbate polarization when the discussion is adversarial. Here, we examine the question whether intergroup interactions around important events affect polarization between majority and minority groups in social networks. We compile data on the religious identity of nearly 700,000 Indian Twitter users engaging in COVID-19-related discourse during 2020. We introduce a new measure for an individual's group conformity based on contextualized embeddings of tweet text, which helps us assess polarization between religious groups. We then use a meta-learning framework to examine heterogeneous treatment effects of intergroup interactions on an individual's group conformity in the light of communal, political, and socio-economic events. We find that for political and social events, intergroup interactions reduce polarization. This decline is weaker for individuals at the extreme who already exhibit high conformity to their group. In contrast, during communal events, intergroup interactions can increase group conformity. Finally, we decompose the differential effects across religious groups in terms of emotions and topics of discussion. The results show that the dynamics of religious polarization are sensitive to the context and have important implications for understanding the role of intergroup interactions.more » « less
-
Around the globe, individuals are affected by exclusion, discrimination, and prejudice targeting individuals from racial, ethnic, and immigrant backgrounds as well as crimes based on gender, nationality, and culture (United Nations General Assembly, 2016). Unfortunately, children are often the targeted victims (Costello & Dillard, 2019). What is not widely understood is that the intergroup biases underlying systemic racism start long before adulthood with children displaying notable signs of intergroup bias, sometimes before entering grade school. Intergroup bias refers to the tendency to evaluate members of one’s own group more favorably than someone not identified with one’s group and is typically associated with prejudicial attitudes. Children are both the victims and the perpetrators of bias. In this review, we provide evidence of how biases emerge in childhood, along with an analysis of the significant role of intergroup friendships on enhancing children’s well-being and reducing prejudice in childhood. The review focuses predominantly on the context of race, with the inclusion of several other categories, such as nationality and religion. Fostering positive cross-group friendships in childhood helps to address the negative long-term consequences of racism, discrimination, and prejudice that emerges in childhood and continues through to adulthood.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- The DOI is not currently available.
