Open Access

ARTICLE

COVID19 Outbreak: A Hierarchical Framework for User Sentiment Analysis

by Ahmed F. Ibrahim¹, M. Hassaballah², Abdelmgeid A. Ali³, Yunyoung Nam^4,*, Ibrahim A. Ibrahim³

1 Department of Computer Science, Faculty of Computer Science, Nahda University, Banisuef, Egypt
2 Department of Computer Science, Faculty of Computers and Information, South Valley University, Qena, Egypt
3 Faculty of Computers and Information, Minia University, Al Minia, Egypt
4 Department of Computer Science and Engineering, Soonchunhyang University, Asan, Korea

* Corresponding Author: Yunyoung Nam. Email:

(This article belongs to the Special Issue: Recent Advances in Deep Learning for Medical Image Analysis)

Computers, Materials & Continua 2022, 70(2), 2507-2524. https://doi.org/10.32604/cmc.2022.018131

Received 26 February 2021; Accepted 26 April 2021; Issue published 27 September 2021

Abstract

Social networking sites in the most modernized world are flooded with large data volumes. Extracting the sentiment polarity of important aspects is necessary; as it helps to determine people’s opinions through what they write. The Coronavirus pandemic has invaded the world and been given a mention in the social media on a large scale. In a very short period of time, tweets indicate unpredicted increase of coronavirus. They reflect people’s opinions and thoughts with regard to coronavirus and its impact on society. The research community has been interested in discovering the hidden relationships from short texts such as Twitter and Weiboa; due to their shortness and sparsity. In this paper, a hierarchical twitter sentiment model (HTSM) is proposed to show people’s opinions in short texts. The proposed HTSM has two main features as follows: constructing a hierarchical tree of important aspects from short texts without a predefined hierarchy depth and width, as well as analyzing the extracted opinions to discover the sentiment polarity on those important aspects by applying a valence aware dictionary for sentiment reasoner (VADER) sentiment analysis. The tweets for each extracted important aspect can be categorized as follows: strongly positive, positive, neutral, strongly negative, or negative. The quality of the proposed model is validated by applying it to a popular product and a widespread topic. The results show that the proposed model outperforms the state-of-the-art methods used in analyzing people’s opinions in short text effectively.

---

Keywords

---

Citations