Offensive Language Detection in Turkish Tweets with Bert Models

Abstract

As the insulting statements increase on the online platform, these negative statements create a reaction and disturb the peace of society. Offensive language detection research has been increased in recent years. This paper explores the effects of the usage of BERT models and fine-tuning techniques on offensive language detection on Turkish tweets. We emphasize the pre-trained model importance on the performance of a downstream task and the importance of the used BERT model.