Cross-Cultural Polarity and Emotion Detection Using Sentiment Analysis and Deep Learning on COVID-19 Related Tweets

Abstract

How different cultures react and respond given a crisis is predominant in a society's norms and political will to combat the situation. Often, the decisions made are necessitated by events, social pressure, or the need of the hour, which may not represent the nation's will. While some are pleased with it, others might show resentment. Coronavirus (COVID-19) brought a mix of similar emotions from the nations towards the decisions taken by their respective governments. Social media was bombarded with posts containing both positive and negative sentiments on the COVID-19, pandemic, lockdown, and hashtags past couple of months. Despite geographically close, many neighboring countries reacted differently to one another. For instance, Denmark and Sweden, which share many similarities, stood poles apart on the decision taken by their respective governments. Yet, their nation's support was mostly unanimous, unlike the South Asian neighboring countries where people showed a lot of anxiety and resentment. The purpose of this study is to analyze reaction of citizens from different cultures to the novel Coronavirus and people's sentiment about subsequent actions taken by different countries. Deep long short-term memory (LSTM) models used for estimating the sentiment polarity and emotions from extracted tweets have been trained to achieve stateof-the-art accuracy on the sentiment140 dataset. The use of emoticons showed a unique and novel way of validating the supervised deep learning models on tweets extracted from Twitter.

Investigating COVID-19 News Across Four Nations: A Topic Modeling and Sentiment Analysis Approach

“…We would also try to improve the accuracy of our RoBERTa model. New and interesting methods have been proposed to detect emotion [21] and sentiment [22] by using models such LTSM and lexicon-based convolutional neural network. We would also try to explore these models in our future studies.…”

“…Samuel et al [20] talked about COVID-19 public sentiment insight and machine learning for tweets classification. Imran et al [21] analyzed tweets from six countries for crosscultural polarity and emotion detection using deep learning method. Huang et al [22] presented sentiment convolutional neural networks to analyze the sentiment of sentences with both contextual and sentiment information of sentiment words.…”

A performance comparison of supervised machine learning models for Covid-19 tweets sentiment analysis

“…The classification is done using LSTM Recurrent Neural Networks (LSTM RNN) model. Another variant of the deep learning model performs sentiment analysis on Covid-19 tweets using the sentiemnt140 dataset [ 23 ]. The results show an improvement over the existing values.…”

Systematic Delineation of Media Polarity on COVID-19 Vaccines in Africa: Computational Linguistic Modeling Study

“…An investigation of the sentiment and public discourse during the pandemic was performed using latent Dirichlet allocation for topic modeling on 1.9 million Tweets written in the English language related to COVID-19 collected from January 23 to March 7, 2020 [ 60 ]. Deep long short-term memory models were used to scrutinize the reaction of citizens, public sentiment, and emotions from different cultures about COVID-19 and the subsequent actions taken by different countries [ 61 ]. These studies reiterate the usefulness of sentiment analysis in the health domain.…”