paper-with-me

홈 › Papers

Semantic Gradients Interactions in SSD: A Case Study in Racial Identity and Hate Speech

2026-05-26 · Felix Ostrowicki, Hubert Plisiecki arxiv

We introduce interaction SSD, an extension of Supervised Semantic Differential that models how semantic meaning varies across moderators such as groups, traits, or conditions making this variation testable and interpretable. The method estimates a main semantic gradient, an interaction gradient, and conditional gradients, all interpretable through standard SSD tools. We illustrate it on the UC Berkeley Measuring Hate Speech corpus, testing whether annotator racial identity moderates hate-speech judgments of comments targeting people of color. The interaction model detects a significant moderation effect: the shared gradient contrasts dehumanizing hostility with counter-speech, while the interaction gradient reveals smaller group-linked differences in which semantic cues predict hate-speech ratings. Interaction SSD makes moderated meaning-outcome relationships statistically testable and interpretable.

📄 PDF Abstract BibTeX arXiv:2605.27322

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Detecting Racial Bias in Jury Selection

2021-03-22 · Jack Dunn, Ying Daisy Zhuo

To support the 2019 U.S. Supreme Court case "Flowers v. Mississippi", APM Reports collated historical court records to assess whether the State exhibited a racial bias in striking potential jurors. This analysis used bac…

feature selection

Racial Disparity in Natural Language Processing: A Case Study of Social Media African-American English

2017-06-30 · Su Lin Blodgett, Brendan O'Connor

We highlight an important frontier in algorithmic fairness: disparity in the quality of natural language processing algorithms when applied to language from authors of different social groups. For example, current system…

FairnessLanguage Identification

Measuring Hidden Bias within Face Recognition via Racial Phenotypes

2021-10-19 · Seyma Yucer, Furkan Tektas, Noura Al Moubayed, Toby P. Breckon

Recent work reports disparate performance for intersectional racial groups across face recognition tasks: face verification and identification. However, the definition of those racial groups has a significant impact on t…

AttributeFace IdentificationFace RecognitionFace Verification

RaceGAN: A Framework for Preserving Individuality while Converting Racial Information for Image-to-Image Translation

2025-09-18 · Mst Tasnim Pervin, George Bebis, Fang Jiang, Alireza Tavakkoli arxiv

Generative adversarial networks (GANs) have demonstrated significant progress in unpaired image-to-image translation in recent years for several applications. CycleGAN was the first to lead the way, although it was restr…

Image-to-Image Translation

Racial Disparities in Debt Collection

2019-10-07 · Jessica LaVoice, Domonkos F. Vamossy

This paper shows that black and Hispanic borrowers are 39% more likely to experience a debt collection judgment than white borrowers, even after controlling for credit scores and other relevant credit attributes. The rac…