Sentiment Analysis for COVID-19 Tweets Using Recurrent Neural Network (RNN) and Bidirectional Encoder Representations (BERT) Models
2021 International Conference on Computing, Electronic and Electrical Engineering, ICE Cube 2021
; 2021.
Article
in English
| Scopus | ID: covidwho-1672724
ABSTRACT
In the last few decades, social media usage has exponentially increased, and people often share information covering various topics of interest. The social media platforms such as Twitter allow users to share images, audio, videos, and text. The textual content can be used as a powerful tool for sentiment analysis. The main goal of this work is to investigate the deep learning models for sentiment analysis of tweets related to COVID-19. The dataset was obtained using tweeter web API between December 20, 2019, to December 15, 2020, and labels were assigned manually as positive, negative, or neutral. Two deep learning models were selected for sentiment analysis:
Recurrent Neural Networks (RNN) and the Bidirectional Encoder Representations (BERT) model. The experimental results showed that both RNN and BERT models were effective for sentiment analysis, resulting in 86.4% and 83.14% accuracy, respectively. © 2021 IEEE.
Full text:
Available
Collection:
Databases of international organizations
Database:
Scopus
Language:
English
Journal:
2021 International Conference on Computing, Electronic and Electrical Engineering, ICE Cube 2021
Year:
2021
Document Type:
Article
Similar
MEDLINE
...
LILACS
LIS