UPennHLP at WNUT-2020 Task 2 : Transformer models for classification of COVID19 posts on Twitter

Arjun Magge, Varad Pimpalkhute, Divya Rallapalli, David Siguenza, Graciela Gonzalez-Hernandez


Abstract
Increasing usage of social media presents new non-traditional avenues for monitoring disease outbreaks, virus transmissions and disease progressions through user posts describing test results or disease symptoms. However, the discussions on the topic of infectious diseases that are informative in nature also span various topics such as news, politics and humor which makes the data mining challenging. We present a system to identify tweets about the COVID19 disease outbreak that are deemed to be informative on Twitter for use in downstream applications. The system scored a F1-score of 0.8941, Precision of 0.9028, Recall of 0.8856 and Accuracy of 0.9010. In the shared task organized as part of the 6th Workshop of Noisy User-generated Text (WNUT), the system was ranked 18th by F1-score and 13th by Accuracy.
Anthology ID:
2020.wnut-1.52
Volume:
Proceedings of the Sixth Workshop on Noisy User-generated Text (W-NUT 2020)
Month:
November
Year:
2020
Address:
Online
Venues:
EMNLP | WNUT
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
378–382
Language:
URL:
https://www.aclweb.org/anthology/2020.wnut-1.52
DOI:
10.18653/v1/2020.wnut-1.52
Bib Export formats:
BibTeX MODS XML EndNote
PDF:
http://aclanthology.lst.uni-saarland.de/2020.wnut-1.52.pdf