Citation: Madni, H.A.; Umer, M.;
Abuzinadah, N.; Hu, Y.-C.; Saidani,
O.; Alsubai, S.; Hamdi, M.; Ashraf, I.
Improving Sentiment Prediction of
Textual Tweets Using Feature Fusion
and Deep Machine Ensemble Model.
Electronics 2023, 12, 1302. https://
doi.org/10.3390/electronics12061302
Academic Editor: Alberto Fernandez
Hilario
Received: 11 December 2022
Revised: 28 December 2022
Accepted: 11 January 2023
Published: 9 March 2023
Copyright: © 2023 by the authors.
Licensee MDPI, Basel, Switzerland.
This article is an open access article
distributed under the terms and
conditions of the Creative Commons
Attribution (CC BY) license (https://
creativecommons.org/licenses/by/
4.0/).
electronics
Article
Improving Sentiment Prediction of Textual Tweets Using
Feature Fusion and Deep Machine Ensemble Model
Hamza Ahmad Madni
1,
* , Muhammad Umer
2
, Nihal Abuzinadah
3
, Yu-Chen Hu
4
, Oumaima Saidani
5
,
Shtwai Alsubai
6
, Monia Hamdi
7
and Imran Ashraf
8,
*
1
College of Electronic and Information Engineering, Beibu Gulf University, Qinzhou 535011, China
2
Department of Computer Science & Information Technology, The Islamia University of Bahawalpur,
Bahawalpur 63100, Pakistan
3
Faculty of Computer Science and Information Technology, King Abdulaziz University, P.O. Box 80200,
Jeddah 21589, Saudi Arabia
4
Department of Computer Science & Information Management, Providence University, Sector 7,
Taiwan Boulevard, Shalu District, Taichung City 43301, Taiwan
5
Department of Information Systems, College of Computer and Information Sciences, Princess Nourah Bint
Abdulrahman University, P.O. Box 84428, Riyadh 11671, Saudi Arabia
6
Department of Computer Science, College of Computer Engineering and Sciences in Al-Kharj,
Prince Sattam Bin Abdulaziz University, P.O. Box 151, Al-Kharj 11942, Saudi Arabia
7
Department of Information Technology, College of Computer and Information Sciences, Princess Nourah Bint
Abdulrahman University, P.O. Box 84428, Riyadh 11671, Saudi Arabia
8
Department of Information and Communication Engineering, Yeungnam University,
Gyeongsan 38541, Republic of Korea
* Correspondence: hamza@bbgu.edu.cn (H.A.M.); imranashraf@ynu.ac.kr (I.A.)
Abstract: Widespread fear and panic has emerged about COVID-19 on social media platforms which
are often supported by falsified and altered content. This mass hysteria creates public anxiety due
to misinformation, misunderstandings, and ignorance of the impact of COVID-19. To assist health
professionals in addressing this epidemic more appropriately at the onset, sentiment analysis can
potentially help the authorities for devising appropriate strategies. This study analyzes tweets related
to COVID-19 using a machine learning approach and offers a high-accuracy solution. Experiments are
performed involving different machine and deep learning models along with various features such as
Word2vec, term-frequency, term-frequency document frequency, and feature fusion of both feature-
generating approaches. The proposed approach combines the extra tree classifier and convolutional
neural network and uses feature fusion to achieve the highest accuracy score of 99%. The proposed
approach obtains far better results than existing sentiment analysis approaches.
Keywords: sentiment analysis; tweet classification; machine learning; COVID-19
1. Introduction
The spread of novel infectious COVID-19 necessitates an appropriate definition of
cases, which are important for clinical diagnosis and health care surveillance. Monitoring
the number of cases over time is essential for the development of effective therapies and the
rate of dissemination. The World Health Organization (WHO) proclaimed the pandemic of
coronavirus on 11 March 2020 [1]. The COVID-19 epidemic has wreaked havoc on the social
and economic conditions of nations all over the world. It is one of the worst pandemics the
entire planet has ever experienced. This COVID-19 pandemic has had a significant impact
on every human’s life [2].
The COVID-19 pandemic had a significant impact on each nation’s medical and
financial position. According to WHO, this pandemic will have an impact on the healthcare
systems of about 75% of the world’s nations by 2020. Beginning with a few Asian and
European nations, COVID-19 will eventually extend to 220 nations worldwide by the
Electronics 2023, 12, 1302. https://doi.org/10.3390/electronics12061302 https://www.mdpi.com/journal/electronics