Towards Patronizing and Condescending Language in Chinese Videos: A Multimodal Dataset and Detector

TL;DR

This paper introduces a new Chinese multimodal dataset and detection method for Patronizing and Condescending Language (PCL), addressing a gap in toxic speech research by including facial cues and multimodal analysis.

Contribution

The paper presents the first Chinese PCL dataset with multimodal annotations and a novel detector leveraging facial expressions, advancing microaggression detection methods.

Findings

The PCLMM dataset contains 715 annotated videos from Bilibili.

The MultiPCL detector effectively combines facial and verbal cues for PCL recognition.

Modality complementarity improves detection accuracy in challenging microaggression scenarios.

Abstract

Patronizing and Condescending Language (PCL) is a form of discriminatory toxic speech targeting vulnerable groups, threatening both online and offline safety. While toxic speech research has mainly focused on overt toxicity, such as hate speech, microaggressions in the form of PCL remain underexplored. Additionally, dominant groups' discriminatory facial expressions and attitudes toward vulnerable communities can be more impactful than verbal cues, yet these frame features are often overlooked. In this paper, we introduce the PCLMM dataset, the first Chinese multimodal dataset for PCL, consisting of 715 annotated videos from Bilibili, with high-quality PCL facial frame spans. We also propose the MultiPCL detector, featuring a facial expression detection module for PCL recognition, demonstrating the effectiveness of modality complementarity in this challenging task. Our work makes an important contribution to advancing microaggression detection within the domain of toxic speech.