Revealing and Predicting Online Persuasion Strategy with Elementary Units

Gaku Morio, Ryo Egawa, Katsuhide Fujita


Abstract
In online arguments, identifying how users construct their arguments to persuade others is important in order to understand a persuasive strategy directly. However, existing research lacks empirical investigations on highly semantic aspects of elementary units (EUs), such as propositions for a persuasive online argument. Therefore, this paper focuses on a pilot study, revealing a persuasion strategy using EUs. Our contributions are as follows: (1) annotating five types of EUs in a persuasive forum, the so-called ChangeMyView, (2) revealing both intuitive and non-intuitive strategic insights for the persuasion by analyzing 4612 annotated EUs, and (3) proposing baseline neural models that identify the EU boundary and type. Our observations imply that EUs definitively characterize online persuasion strategies.
Anthology ID:
D19-1653
Volume:
Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)
Month:
November
Year:
2019
Address:
Hong Kong, China
Venues:
EMNLP | IJCNLP
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
6274–6279
Language:
URL:
https://www.aclweb.org/anthology/D19-1653
DOI:
10.18653/v1/D19-1653
Bib Export formats:
BibTeX MODS XML EndNote
PDF:
http://aclanthology.lst.uni-saarland.de/D19-1653.pdf