Linguistically Differentiating Acts and Recalls of Racial Microaggressions on Social Media

TL;DR

This study tackles the problem of distinguishing acts from recalls of racial microaggressions on social media by building the RAMA corpus (2,000 acts and 1,264 recalls) and applying both state-of-the-art NLP classifiers and qualitative analyses. It leverages Integrated Gradients to interpret model decisions and identifies distinct and overlapping themes that characterize acts and recalls, revealing practical challenges for content moderation in distinguishing false positives and false negatives. The authors validate labels via workshops with Black participants, ensuring culturally informed ground truth, and discuss implications for explainable moderation, guideline refinement, and counter-storytelling within Critical Race Theory. The work advances a more nuanced, context-aware approach to moderating race-related discourse online and highlights how linguistic patterns can inform safer, more inclusive online spaces.

Abstract

In this work, we examine the linguistic signature of online racial microaggressions (acts) and how it differs from that of personal narratives recalling experiences of such aggressions (recalls) by Black social media users. We manually curate and annotate a corpus of acts and recalls from in-the-wild social media discussions, and verify labels with Black workshop participants. We leverage Natural Language Processing (NLP) and qualitative analysis on this data to classify (RQ1), interpret (RQ2), and characterize (RQ3) the language underlying acts and recalls of racial microaggressions in the context of racism in the U.S. Our findings show that neural language models (LMs) can classify acts and recalls with high accuracy (RQ1) with contextual words revealing themes that associate Blacks with objects that reify negative stereotypes (RQ2). Furthermore, overlapping linguistic signatures between acts and recalls serve functionally different purposes (RQ3), providing broader implications to the current challenges in content moderation systems on social media.