5 papers
IYKYK (But AI Doesn't): Automated Content Moderation Does Not Capture Communities' Heterogeneous Attitudes Towards Reclaimed Language
Christina Chance, Rebecca Pattichis, Arjun Subramonian +4
Reclaimed slur usage is a common and meaningful practice online for many marginalized communities. It serves as a source of solidarity, identity, and shared experience. However, co…
Reinforcing Stereotypes of Anger: Emotion AI on African American Vernacular English
Rebecca Dorn, Christina Chance, Casandra Rusti +4
Automated emotion detection is widely used in applications ranging from well-being monitoring to high-stakes domains like mental health and hiring. However, models often rely on an…
ModelCitizens: Representing Community Voices in Online Safety
Ashima Suvarna, Christina Chance, Karolina Naranjo +4
Automatic toxic language detection is critical for creating safe, inclusive online spaces. However, it is a highly subjective task, with perceptions of toxic language shaped by com…
Will the Prince Get True Love's Kiss? On the Model Sensitivity to Gender Perturbation over Fairytale Texts
Christina Chance, Da Yin, Dakuo Wang +1
In this paper, we study whether language models are affected by learned gender stereotypes during the comprehension of stories. Specifically, we investigate how models respond to g…
Leveraging Language Models to Detect Greenwashing
Avalon Vinella, Margaret Capetz, Rebecca Pattichis +3
In recent years, climate change repercussions have increasingly captured public interest. Consequently, corporations are emphasizing their environmental efforts in sustainability r…