FastThaiCaps: A Transformer based Capsule Network for Hate Speech Detection in Thai Language

Abstract

The advent of technology has led to people sharing their views openly like never before. Parallelly, cyberbullying and hate speech content have also increased as a side effect that is potentially hazardous to society. While plenty of research is going on to detect online hate speech in English, there is very little research on the Thai language. To investigate how noisy Thai posts can be handled effectively, in this work, we have developed a two-channel deep learning model FastThaiCaps based on BERT and FastText embedding along with a capsule network. The input to one channel is the BERT language model, and that to the other is the pre-trained FastText embedding. Our model has been evaluated on a benchmark Thai dataset categorized into four categories, i.e., peace speech, neutral speech, level-1 hate speech, and level-2 hate speech. Experiments show that FastThaiCaps outperforms state-of-the-art methods by up to 3.11% in terms F1 score.