Search for: All records

We introduce an open-source platform for annotating body-worn video (BWV) footage aimed at enhancing transparency and accountability in policing. Despite the widespread adoption of BWVs in police departments, analyzing the vast amount of footage generated has presented significant challenges. This is primarily due to resource constraints, the sensitive nature of the data, which limits widespread access, and consequently, lack of annotations for training machine learning models. Our platform, called CVAT-BWV, offers a secure, locally hosted annotation environment that integrates several AI tools to assist in annotating multimodal data. With features such as automatic speech recognition, speaker diarization, object detection, and face recognition, CVAT-BWV aims to reduce the manual annotation workload, improve annotation quality, and allow for capturing perspectives from a diverse population of annotators. This tool aims to streamline the collection of annotations and the building of models, enhancing the use of BWV data for oversight and learning purposes to uncover insights into police-civilian interactions. 

Abstract 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. 

Abstract Humans use language toward hateful ends, inciting violence and genocide, intimidating and denigrating others based on their identity. Despite efforts to better address the language of hate in the public sphere, the psychological processes involved in hateful language remain unclear. In this work, we hypothesize that morality and hate are concomitant in language. In a series of studies, we find evidence in support of this hypothesis using language from a diverse array of contexts, including the use of hateful language in propaganda to inspire genocide (Study 1), hateful slurs as they occur in large text corpora across a multitude of languages (Study 2), and hate speech on social-media platforms (Study 3). In post hoc analyses focusing on particular moral concerns, we found that the type of moral content invoked through hate speech varied by context, with Purity language prominent in hateful propaganda and online hate speech and Loyalty language invoked in hateful slurs across languages. Our findings provide a new psychological lens for understanding hateful language and points to further research into the intersection of morality and hate, with practical implications for mitigating hateful rhetoric online. 

Technological innovations have become a key driver of societal advancements. Nowhere is this more evident than in the field of machine learning (ML), which has developed algorithmic models that shape our decisions, behaviors, and outcomes. These tools have widespread use, in part, because they can synthesize massive amounts of data to make seemingly objective recommendations. Yet, in the past few years, the ML community has been drawing attention to the need for caution when interpreting and using these models. This is because these models are created by humans, from data generated by humans, whose psychology allows for various biases that impact how the models are developed, trained, tested, and interpreted. As psychologists, we thus face a fork in the road: Down the first path, we can continue to use these models without examining and addressing these critical flaws and rely on computer scientists to try to mitigate them. Down the second path, we can turn our expertise in bias toward this growing field, collaborating with computer scientists to reduce the models’ deleterious outcomes. This article serves to light the way down the second path by identifying how extant psychological research can help examine and curtail bias in ML models. 

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.