COVID19 Outbreak: A Hierarchical Framework for User Sentiment Analysis

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.