Fraunhofer SIT@SMM4H’22: Learning to Predict Stances and Premises in Tweets related to COVID-19 Health Orders Using Generative Models

Raphael Frick, Martin Steinebach


Abstract
This paper describes the system used to predict stances towards health orders and to detect premises in Tweets as part of the Social Media Mining for Health 2022 (SMM4H) shared task. It takes advantage of GPT-2 to generate new labeled data samples which are used together with pre-labeled and unlabeled data to fine-tune an ensemble of GAN-BERT models. First experiments on the validation set yielded good results, although it also revealed that the proposed architecture is more suited for sentiment analysis. The system achieved a score of 0.4258 for the stance and 0.3581 for the premise detection on the test set.
Anthology ID:
2022.smm4h-1.31
Volume:
Proceedings of The Seventh Workshop on Social Media Mining for Health Applications, Workshop & Shared Task
Month:
October
Year:
2022
Address:
Gyeongju, Republic of Korea
Editors:
Graciela Gonzalez-Hernandez, Davy Weissenbacher
Venue:
SMM4H
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
111–113
Language:
URL:
https://aclanthology.org/2022.smm4h-1.31
DOI:
Bibkey:
Cite (ACL):
Raphael Frick and Martin Steinebach. 2022. Fraunhofer SIT@SMM4H’22: Learning to Predict Stances and Premises in Tweets related to COVID-19 Health Orders Using Generative Models. In Proceedings of The Seventh Workshop on Social Media Mining for Health Applications, Workshop & Shared Task, pages 111–113, Gyeongju, Republic of Korea. Association for Computational Linguistics.
Cite (Informal):
Fraunhofer SIT@SMM4H’22: Learning to Predict Stances and Premises in Tweets related to COVID-19 Health Orders Using Generative Models (Frick & Steinebach, SMM4H 2022)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-4/2022.smm4h-1.31.pdf