A Comprehensive Analysis of Transformer-Deep Neural Network Models in Twitter Disaster Detection

Vimala Balakrishnan (), Zhongliang Shi, Chuan Liang Law, Regine Lim, Lee Leng Teh, Yue Fan and Jeyarani Periasamy
Additional contact information
Vimala Balakrishnan: Faculty of Computer Science and Information Technology, Universiti Malaya, Kuala Lumpur 50603, Malaysia
Zhongliang Shi: Faculty of Computer Science and Information Technology, Universiti Malaya, Kuala Lumpur 50603, Malaysia
Chuan Liang Law: Malayan Banking Berhad, Kuala Lumpur 50050, Malaysia
Regine Lim: Faculty of Computer Science and Information Technology, Universiti Malaya, Kuala Lumpur 50603, Malaysia
Lee Leng Teh: Faculty of Computer Science and Information Technology, Universiti Malaya, Kuala Lumpur 50603, Malaysia
Yue Fan: Faculty of Computer Science and Information Technology, Universiti Malaya, Kuala Lumpur 50603, Malaysia
Jeyarani Periasamy: Faculty of Data Science and Information Technology, INTI International University, Nilai 71800, Malaysia

Mathematics, 2022, vol. 10, issue 24, 1-14

Abstract: Social media platforms such as Twitter are a vital source of information during major events, such as natural disasters. Studies attempting to automatically detect textual communications have mostly focused on machine learning and deep learning algorithms. Recent evidence shows improvement in disaster detection models with the use of contextual word embedding techniques (i.e., transformers) that take the context of a word into consideration, unlike the traditional context-free techniques; however, studies regarding this model are scant. To this end, this paper investigates a selection of ensemble learning models by merging transformers with deep neural network algorithms to assess their performance in detecting informative and non-informative disaster-related Twitter communications. A total of 7613 tweets were used to train and test the models. Results indicate that the ensemble models consistently yield good performance results, with F-score values ranging between 76% and 80%. Simpler transformer variants, such as ELECTRA and Talking-Heads Attention, yielded comparable and superior results compared to the computationally expensive BERT, with F-scores ranging from 80% to 84%, especially when merged with Bi-LSTM. Our findings show that the newer and simpler transformers can be used effectively, with less computational costs, in detecting disaster-related Twitter communications.

Keywords: disaster; Twitter; deep neural network; transformers; ensemble (search for similar items in EconPapers)
JEL-codes: C (search for similar items in EconPapers)
Date: 2022
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (1)

Downloads: (external link)
https://www.mdpi.com/2227-7390/10/24/4664/pdf (application/pdf)
https://www.mdpi.com/2227-7390/10/24/4664/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jmathe:v:10:y:2022:i:24:p:4664-:d:998091

Access Statistics for this article

Mathematics is currently edited by Ms. Emma He

More articles in Mathematics from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().