MBTI Personality Prediction for Fictional Characters Using Movie Scripts

Yisi Sang, Xiangyang Mou, Mo Yu, Dakuo Wang, Jing Li, Jeffrey Stanton


Abstract
An NLP model that understands stories should be able to understand the characters in them. To support the development of neural models for this purpose, we construct a benchmark, Story2Personality. The task is to predict a movie character’s MBTI or Big 5 personality types based on the narratives of the character. Experiments show that our task is challenging for the existing text classification models, as none is able to largely outperform random guesses. We further proposed a multi-view model for personality prediction using both verbal and non-verbal descriptions, which gives improvement compared to using only verbal descriptions. The uniqueness and challenges in our dataset call for the development of narrative comprehension techniques from the perspective of understanding characters.
Anthology ID:
2022.findings-emnlp.500
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2022
Month:
December
Year:
2022
Address:
Abu Dhabi, United Arab Emirates
Editors:
Yoav Goldberg, Zornitsa Kozareva, Yue Zhang
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
6715–6724
Language:
URL:
https://aclanthology.org/2022.findings-emnlp.500
DOI:
10.18653/v1/2022.findings-emnlp.500
Bibkey:
Cite (ACL):
Yisi Sang, Xiangyang Mou, Mo Yu, Dakuo Wang, Jing Li, and Jeffrey Stanton. 2022. MBTI Personality Prediction for Fictional Characters Using Movie Scripts. In Findings of the Association for Computational Linguistics: EMNLP 2022, pages 6715–6724, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
Cite (Informal):
MBTI Personality Prediction for Fictional Characters Using Movie Scripts (Sang et al., Findings 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.findings-emnlp.500.pdf