A Community-Centric Perspective for Characterizing and Detecting Anti-Asian Violence-Provoking Speech

TL;DR

This study introduces a community-centric approach to characterizing and detecting anti-Asian violence-provoking speech on Twitter, highlighting the challenges of current classifiers and emphasizing the need for proactive interventions during crises.

Contribution

It develops a new codebook and dataset for violence-provoking speech, and compares NLP classifiers' effectiveness in detecting this harmful speech type.

Findings

Detection of violence-provoking speech is less accurate than hate speech ($F_1=0.69$ vs. 0.89).

Natural language classifiers struggle with reliably identifying violence-provoking content.

Community-based resources and tools are provided for large-scale detection.

Abstract

Violence-provoking speech -- speech that implicitly or explicitly promotes violence against the members of the targeted community, contributed to a massive surge in anti-Asian crimes during the pandemic. While previous works have characterized and built tools for detecting other forms of harmful speech, like fear speech and hate speech, our work takes a community-centric approach to studying anti-Asian violence-provoking speech. Using data from ~420k Twitter posts spanning a 3-year duration (January 1, 2020 to February 1, 2023), we develop a codebook to characterize anti-Asian violence-provoking speech and collect a community-crowdsourced dataset to facilitate its large-scale detection using state-of-the-art classifiers. We contrast the capabilities of natural language processing classifiers, ranging from BERT-based to LLM-based classifiers, in detecting violence-provoking speech with their capabilities to detect anti-Asian hateful speech. In contrast to prior work that has demonstrated the effectiveness of such classifiers in detecting hateful speech ($F_1 = 0.89$), our work shows that accurate and reliable detection of violence-provoking speech is a challenging task ($F_1 = 0.69$). We discuss the implications of our findings, particularly the need for proactive interventions to support Asian communities during public health crises. The resources related to the study are available at https://claws-lab.github.io/violence-provoking-speech/.