Computational Detection of Narrativity: A Comparison Using Textual Features and Reader Response

Max Steg, Karlo Slot, Federico Pianzola


Abstract
The task of computational textual narrative detection focuses on detecting the presence of narrative parts, or the degree of narrativity in texts. In this work, we focus on detecting the local degree of narrativity in texts, using short text passages. We performed a human annotation experiment on 325 English texts ranging across 20 genres to capture readers’ perception by means of three cognitive aspects: suspense, curiosity, and surprise. We then employed a linear regression model to predict narrativity scores for 17,372 texts. When comparing our average annotation scores to similar annotation experiments with different cognitive aspects, we found that Pearson’s r ranges from .63 to .75. When looking at the calculated narrative probabilities, Pearson’s r is .91. We found that it is possible to use suspense, curiosity and surprise to detect narrativity. However, there are still differences between methods. This does not imply that there are inherently correct methods, but rather suggests that the underlying definition of narrativity is a determining factor for the results of the computational models employed.
Anthology ID:
2022.latechclfl-1.13
Volume:
Proceedings of the 6th Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature
Month:
October
Year:
2022
Address:
Gyeongju, Republic of Korea
Editors:
Stefania Degaetano, Anna Kazantseva, Nils Reiter, Stan Szpakowicz
Venue:
LaTeCHCLfL
SIG:
SIGHUM
Publisher:
International Conference on Computational Linguistics
Note:
Pages:
105–114
Language:
URL:
https://aclanthology.org/2022.latechclfl-1.13
DOI:
Bibkey:
Cite (ACL):
Max Steg, Karlo Slot, and Federico Pianzola. 2022. Computational Detection of Narrativity: A Comparison Using Textual Features and Reader Response. In Proceedings of the 6th Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature, pages 105–114, Gyeongju, Republic of Korea. International Conference on Computational Linguistics.
Cite (Informal):
Computational Detection of Narrativity: A Comparison Using Textual Features and Reader Response (Steg et al., LaTeCHCLfL 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.latechclfl-1.13.pdf