From None to Severe: Predicting Severity in Movie Scripts
This addresses a domain-specific problem for content rating systems, but it is incremental as it builds on existing methods for text classification.
The paper tackles predicting the severity of age-restricted content in movies from dialogue scripts, using a siamese network-based multitask framework, and reports that it outperforms the previous state-of-the-art model.
In this paper, we introduce the task of predicting severity of age-restricted aspects of movie content based solely on the dialogue script. We first investigate categorizing the ordinal severity of movies on 5 aspects: Sex, Violence, Profanity, Substance consumption, and Frightening scenes. The problem is handled using a siamese network-based multitask framework which concurrently improves the interpretability of the predictions. The experimental results show that our method outperforms the previous state-of-the-art model and provides useful information to interpret model predictions. The proposed dataset and source code are publicly available at our GitHub repository.