From None to Severe: Predicting Severity in Movie Scripts

Yigeng Zhang, Mahsa Shafaei, Fabio Gonzalez, Thamar Solorio


Abstract
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.
Anthology ID:
2021.findings-emnlp.332
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2021
Month:
November
Year:
2021
Address:
Punta Cana, Dominican Republic
Editors:
Marie-Francine Moens, Xuanjing Huang, Lucia Specia, Scott Wen-tau Yih
Venue:
Findings
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
3951–3956
Language:
URL:
https://aclanthology.org/2021.findings-emnlp.332
DOI:
10.18653/v1/2021.findings-emnlp.332
Bibkey:
Cite (ACL):
Yigeng Zhang, Mahsa Shafaei, Fabio Gonzalez, and Thamar Solorio. 2021. From None to Severe: Predicting Severity in Movie Scripts. In Findings of the Association for Computational Linguistics: EMNLP 2021, pages 3951–3956, Punta Cana, Dominican Republic. Association for Computational Linguistics.
Cite (Informal):
From None to Severe: Predicting Severity in Movie Scripts (Zhang et al., Findings 2021)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-3/2021.findings-emnlp.332.pdf
Video:
 https://preview.aclanthology.org/nschneid-patch-3/2021.findings-emnlp.332.mp4
Code
 ritual-uh/predicting-severity-in-movie-scripts