A Wide & Deep Learning Approach for Covid-19 Tweet Classification
14th Mexican Conference on Pattern Recognition, MCPR 2022
; 13264 LNCS:225-234, 2022.
Article
in English
| Scopus | ID: covidwho-1919714
ABSTRACT
Public health surveillance via social media can be a useful tool to identify and track potential cases of a disease. The aim of this research was to design a method for identifying tweets describing potential Covid-19 cases. The proposed method uses a Wide & Deep (W&D) architecture, which combines two learning branches fed from different features to improve classification effectiveness. The deep branch uses a BERT-type model, while the wide branch considers two different lexical-based features. It was evaluated on the data from Task 5 of the Social Media Mining For Health (#SMM4H) 2021 competition. Results show that the proposed W&D method performed better than the wide-only and deep-only models, achieving an F1-score of 0.79 which matches the results of the 1st place ensemble-model. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.
Covid-19; Data mining; Natural language processing; Social media; Text classification; Wide & Deep; Classification (of information); Deep learning; Learning algorithms; Natural language processing systems; Social networking (online); Text processing; Deep architectures; Language processing; Learning approach; Natural languages; Public health surveillances
Full text:
Available
Collection:
Databases of international organizations
Database:
Scopus
Language:
English
Journal:
14th Mexican Conference on Pattern Recognition, MCPR 2022
Year:
2022
Document Type:
Article
Similar
MEDLINE
...
LILACS
LIS