HSD Shared Task in VLSP Campaign 2019:Hate Speech Detection for Social Good

TL;DR

This paper details the organization and participation in the HSD shared task at VLSP 2019, focusing on detecting hate speech in Vietnamese Facebook messages through a large-scale multi-class classification challenge.

Contribution

It introduces a large-scale Vietnamese hate speech dataset and presents a multi-class classification task to advance hate speech detection research.

Findings

High participation with 71 teams and 380 submissions.

Successful organization of a large-scale hate speech detection challenge.

Engagement of the Vietnamese NLP community in social good tasks.

Abstract

The paper describes the organisation of the "HateSpeech Detection" (HSD) task at the VLSP workshop 2019 on detecting the fine-grained presence of hate speech in Vietnamese textual items (i.e., messages) extracted from Facebook, which is the most popular social network site (SNS) in Vietnam. The task is organised as a multi-class classification task and based on a large-scale dataset containing 25,431 Vietnamese textual items from Facebook. The task participants were challenged to build a classification model that is capable of classifying an item to one of 3 classes, i.e., "HATE", "OFFENSIVE" and "CLEAN". HSD attracted a large number of participants and was a popular task at VLSP 2019. In particular, there were 71 teams signed up for the task, 14 of them submitted results with 380 valid submissions from 20th September 2019 to 4th October 2019.