How Hateful are Movies? A Study and Prediction on Movie Subtitles
This work addresses hate speech detection in movies for content moderation, but it is incremental as it applies existing methods to a new domain.
The researchers tackled hate speech detection in movies by creating a new dataset of annotated movie subtitles and applying transfer learning from social media datasets. Their BERT model achieved a 77% macro-averaged F1-score, demonstrating the efficacy of this approach.
In this research, we investigate techniques to detect hate speech in movies. We introduce a new dataset collected from the subtitles of six movies, where each utterance is annotated either as hate, offensive or normal. We apply transfer learning techniques of domain adaptation and fine-tuning on existing social media datasets, namely from Twitter and Fox News. We evaluate different representations, i.e., Bag of Words (BoW), Bi-directional Long short-term memory (Bi-LSTM), and Bidirectional Encoder Representations from Transformers (BERT) on 11k movie subtitles. The BERT model obtained the best macro-averaged F1-score of 77%. Hence, we show that transfer learning from the social media domain is efficacious in classifying hate and offensive speech in movies through subtitles.