Sequence Classification of Tweets with Transfer Learning via BERT in the Field of Disaster Management

Naaz, Sumera and Abedin, Zain Ul and Rizvi, Danish Raza (2021) Sequence Classification of Tweets with Transfer Learning via BERT in the Field of Disaster Management. EAI Endorsed Transactions on Scalable Information Systems, 8 (31). e8. ISSN 2032-9407

[img]
Preview
Text
eai.23-3-2021.169071.pdf
Available under License Creative Commons Attribution No Derivatives.

Download (2MB) | Preview

Abstract

Twitter is extensively used as an information-sharing platform during any kind of emergency like disasters etc. People tweet useful information about disaster-related events such as evacuations, volunteer need, help, warnings etc. This data is sometimes very useful for rescue teams, NGOs, military and various other government and private organisations who are tasked with responsibilities to save lives and provide volunteers. This data can also be used to analyze disaster behaviour. In this paper, we have collected labelled tweets from crisisLexT26 and crisisNLP and classified them into seven labels on the basis of information provided by them. The data was heavily skewed. So to improve the accuracy of classifiers, we have applied various techniques as a result of which we have created two datasets (Imbalanced and Balanced). We have compared the performance of various BERT-based models on these two datasets. For sequence classification, a balanced dataset performs better than an imbalanced dataset. We can improve accuracy of classifiers to great extent by adopting good data preprocessing and data splitting techniques.

Item Type: Article
Uncontrolled Keywords: BERT (Bidirectional Encoder Representation from Transformers), Tweet classification, Balanced Dataset, Imbalanced Dataset, Disaster Management, Natural Language Processing
Subjects: Q Science > QA Mathematics > QA75 Electronic computers. Computer science
QA75 Electronic computers. Computer science
T Technology > T Technology (General)
Depositing User: EAI Editor IV
Date Deposited: 09 Jul 2021 08:31
Last Modified: 09 Jul 2021 08:31
URI: https://eprints.eudl.eu/id/eprint/4397

Actions (login required)

View Item View Item