ETCNN: Extra Tree and Convolutional Neural Network-based Ensemble Model for COVID-19 Tweets Sentiment Classification

Muhammad Umer; Saima Sadiq; Hanen Karamti; Ala' Abdulmajid Eshmawi; Michele Nappi; Muhammad Usman Sana; Imran Ashraf

doi:10.1016/j.patrec.2022.11.012

ETCNN: Extra Tree and Convolutional Neural Network-based Ensemble Model for COVID-19 Tweets Sentiment Classification

Pattern Recognit Lett. 2022 Dec:164:224-231. doi: 10.1016/j.patrec.2022.11.012. Epub 2022 Nov 15.

Authors

Muhammad Umer¹, Saima Sadiq², Hanen Karamti³, Ala' Abdulmajid Eshmawi⁴, Michele Nappi⁵, Muhammad Usman Sana⁶, Imran Ashraf⁷

Affiliations

¹ Department of Computer Science & Information Technology, The Islamia University of Bahawalpur, Bahawalpur, 63100, Pakistan.
² Department of Computer Science, Khwaja Fareed University of Engineering and Information Technology, Rahim Yar Khan, Pakistan.
³ Department of computer sciences, College of Computer and Information Sciences, Princess Nourah bint Abdulrahman University, P.O.Box 84428, Riyadh 11671, Saudi Arabia.
⁴ Department of Cybersecurity, University of Jeddah, Saudi Arabia.
⁵ Department of Computer Science, University of Salerno, Fisciano, Italy.
⁶ College of Computer Science Technology, Xian University of Science and Technology, Xian, Shaanxi 710054, China.
⁷ Information and Communication Engineering, Yeungnam University, Gyeongsan 38541, Korea.

Abstract

Pandemics influence people negatively and people experience fear and disappointment. With the global outspread of COVID-19, the sentiments of the general public are substantially influenced, and analyzing their sentiments could help to devise corresponding policies to alleviate negative sentiments. Often the data collected from social media platforms is unstructured leading to low classification accuracy. This study brings forward an ensemble model where the benefits of handcrafted features and automatic feature extraction are combined by machine learning and deep learning models. Unstructured data is obtained, preprocessed, and annotated using TextBlob and VADER before training machine learning models. Similarly, the efficiency of Word2Vec, TF, and TF-IDF features is also analyzed. Results reveal the better performance of the extra tree classifier when trained with TF-IDF features from TextBlob annotated data. Overall, machine learning models perform better with TF-IDF and TextBlob. The proposed model obtains superior performance using both annotation techniques with 0.97 and 0.95 scores of accuracy using TextBlob and VADER respectively with Word2Vec features. Results reveal that use of machine learning and deep learning models together with a voting criterion tends to yield better results than other machine learning models. Analysis of sentiments indicates that predominantly people possess negative sentiments regarding COVID-19.

Keywords: COVID-19; Ensemble model; Health informatics; Neuroinformatics; Sentiment analysis.