Adapting Transformers for Detecting Emergency Events on Social Media

Emanuela Boros, Gaël Lejeune, Mickaël Coustaty, Antoine Doucet

2022

Abstract

Detecting emergency events on social media could facilitate disaster monitoring by categorizing and prioritizing tweets in catastrophic situations to assist emergency service operators. However, the high noise levels in tweets, combined with the limited publicly available datasets have rendered the task difficult. In this paper, we propose an enhanced multitask Transformer-based model that highlights the importance of entities, event descriptions, and hashtags in tweets. This approach includes a Transformer encoder with several layers over the sequential token representation provided by a pre-trained language model that acts as a task adapter for detecting emergency events in noisy data. We conduct an evaluation on the Text REtrieval Conference (TREC) 2021 Incident Streams (IS) track dataset, and we conclude that our proposed approach brought considerable improvements to emergency social media classification.

Paper Citation

in Harvard Style

Boros E., Lejeune G., Coustaty M. and Doucet A. (2022). Adapting Transformers for Detecting Emergency Events on Social Media. In Proceedings of the 14th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management (IC3K 2022) - Volume 1: KDIR; ISBN 978-989-758-614-9, SciTePress, pages 300-306. DOI: 10.5220/0011559800003335

in Bibtex Style

@conference{kdir22,
author={Emanuela Boros and Gaël Lejeune and Mickaël Coustaty and Antoine Doucet},
title={Adapting Transformers for Detecting Emergency Events on Social Media},
booktitle={Proceedings of the 14th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management (IC3K 2022) - Volume 1: KDIR},
year={2022},
pages={300-306},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0011559800003335},
isbn={978-989-758-614-9},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 14th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management (IC3K 2022) - Volume 1: KDIR
TI - Adapting Transformers for Detecting Emergency Events on Social Media
SN - 978-989-758-614-9
AU - Boros E.
AU - Lejeune G.
AU - Coustaty M.
AU - Doucet A.
PY - 2022
SP - 300
EP - 306
DO - 10.5220/0011559800003335
PB - SciTePress