Modelling Suspense in Short Stories as Uncertainty Reduction over Neural Representation

David Wilmot, Frank Keller


Abstract
Suspense is a crucial ingredient of narrative fiction, engaging readers and making stories compelling. While there is a vast theoretical literature on suspense, it is computationally not well understood. We compare two ways for modelling suspense: surprise, a backward-looking measure of how unexpected the current state is given the story so far; and uncertainty reduction, a forward-looking measure of how unexpected the continuation of the story is. Both can be computed either directly over story representations or over their probability distributions. We propose a hierarchical language model that encodes stories and computes surprise and uncertainty reduction. Evaluating against short stories annotated with human suspense judgements, we find that uncertainty reduction over representations is the best predictor, resulting in near human accuracy. We also show that uncertainty reduction can be used to predict suspenseful events in movie synopses.
Anthology ID:
2020.acl-main.161
Volume:
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics
Month:
July
Year:
2020
Address:
Online
Editors:
Dan Jurafsky, Joyce Chai, Natalie Schluter, Joel Tetreault
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1763–1788
Language:
URL:
https://aclanthology.org/2020.acl-main.161
DOI:
10.18653/v1/2020.acl-main.161
Bibkey:
Cite (ACL):
David Wilmot and Frank Keller. 2020. Modelling Suspense in Short Stories as Uncertainty Reduction over Neural Representation. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 1763–1788, Online. Association for Computational Linguistics.
Cite (Informal):
Modelling Suspense in Short Stories as Uncertainty Reduction over Neural Representation (Wilmot & Keller, ACL 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.acl-main.161.pdf
Video:
 http://slideslive.com/38928796
Code
 dwlmt/Story-Untangling
Data
TRIPODWritingPrompts