A Risk Communication Event Detection Model via Contrastive Learning

Mingi Shin, Sungwon Han, Sungkyu Park, Meeyoung Cha


Abstract
This paper presents a time-topic cohesive model describing the communication patterns on the coronavirus pandemic from three Asian countries. The strength of our model is two-fold. First, it detects contextualized events based on topical and temporal information via contrastive learning. Second, it can be applied to multiple languages, enabling a comparison of risk communication across cultures. We present a case study and discuss future implications of the proposed model.
Anthology ID:
2020.nlp4if-1.5
Volume:
Proceedings of the 3rd NLP4IF Workshop on NLP for Internet Freedom: Censorship, Disinformation, and Propaganda
Month:
December
Year:
2020
Address:
Barcelona, Spain (Online)
Editors:
Giovanni Da San Martino, Chris Brew, Giovanni Luca Ciampaglia, Anna Feldman, Chris Leberknight, Preslav Nakov
Venue:
NLP4IF
SIG:
Publisher:
International Committee on Computational Linguistics (ICCL)
Note:
Pages:
39–43
Language:
URL:
https://aclanthology.org/2020.nlp4if-1.5
DOI:
Bibkey:
Cite (ACL):
Mingi Shin, Sungwon Han, Sungkyu Park, and Meeyoung Cha. 2020. A Risk Communication Event Detection Model via Contrastive Learning. In Proceedings of the 3rd NLP4IF Workshop on NLP for Internet Freedom: Censorship, Disinformation, and Propaganda, pages 39–43, Barcelona, Spain (Online). International Committee on Computational Linguistics (ICCL).
Cite (Informal):
A Risk Communication Event Detection Model via Contrastive Learning (Shin et al., NLP4IF 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.nlp4if-1.5.pdf