Hate speech detection for Banjarese languages on Instagram: a dataset and preliminary study

The Hate Speech Detection for Banjarese Languages dataset is a curated collection of text data from Instagram. It focuses on identifying hate speech in Banjarese language on Instagram, comprising 15,481 comments. Of these, 2,039 are labeled as hate speech, while 13,442 are non-hate speech. The dataset enables the development of accurate hate speech detection systems for the Banjarese language.