Despite recent advances in natural language processing, detecting hate speech online is still a difficult issue. Contextual information encoding into detecting systems is a major challenge. The present study examines whether nasty Facebook comments especially target migrants in order to determine who is the target of hate speech on Dutch social media. The researchers manually annotate conversational context and evaluate how various contextual aspects affect BERTje, a language model based on Dutch transformers. Results demonstrate that adding pertinent context greatly enhances model performance.https://aclanthology.org/2022.trac-1.5Share this: Click to share on Facebook (Opens in new window) Facebook Click to share on X (Opens in new window) X Like this:Like Loading... Post navigation MemHateCaptioning: Enhancing Hate Speech Detection in Memes with Context-Aware Captioning and Chain-of-Thought (ACM Digital Library) Hate and Offensive Text Data Detection using NLP Model (IJRPR)