Dataset for identification of queerphobia

While social media platforms have implemented many algorithmic approaches to moderating hate speech, there is a lack of datasets on queerphobia which has impeded efforts automatically recognize and moderate queerphobic speech online. Queerphobic that intended degrade, insult, or incite violence prejudicial action against queer people, who are those from sexuality, gender, romantic minority. This results in worsened mental emotional outcomes for people can contribute anti-queer violence. The goal this study create dataset YouTube comments further identify speech. To construct dataset, 10,000 were sourced videos represent queerness. Then, volunteers manually annotated each comment accordance with specific guidelines. Various natural language processing (NLP) models used extract features the text, several classifiers these categorize as non-queerphobic. These NLP illustrate baseline performance data. In making we hope research recognition digital make safer people. be found at https://github.com/ShivumB/dataset-for-identification-of-queerphobia.