Does Social Media Follow News Media?: A Comparative Sentiment Analysis During the COVID-19 Pandemic

Does Social Media Follow News Media?: A Comparative Sentiment Analysis During the COVID-19 Pandemic

Hemangee De, Koushik Deb
DOI: 10.4018/IJICTHD.2021100102
OnDemand:
(Individual Articles)
Available
$37.50
No Current Special Offers
TOTAL SAVINGS: $37.50

Abstract

Today, sentiment analysis is in high use to understand user reactions. In this paper, the authors have discussed this topic using news and Twitter texts as sources of data. They use TextBlob, VADER, and IBM Watson NLU as sentiment analysis tools. The news sentiment analysis data is from January to July 2020, classified under each tool. The authors get almost the same result from all of them. February shows having the maximum negative polarity news, followed by June. While Twitter data of each month when classified under each sentiment analysis tool shows the same kind of result for all the months, March has the maximum negative polarity and maximum positive polarity is seen in January. The aim of this paper is to show that sentiment analysis on newspaper content can help common people to know the bias in newspapers to prevent more negative impact on readers especially during a pandemic like COVID-19. The comparison drawn between the news data sentiment analysis and the same with Twitter data has a good correlation but still shows a difference in sentiment.
Article Preview
Top

Introduction

Covid-19 Situation has led to panic in the minds of humans. News is the medium through which we can know the information about the rise in cases due to Covid-19 infection all over the world. Negativity in daily news is impacting human psychology and causing tension. This pandemic has caused a dramatic loss of human life worldwide and presents an unprecedented challenge to public health, food systems and the world of work. The economic and social disruption caused by the pandemic is devastating: tens of millions of people are at risk of falling into extreme poverty, while the number of undernourished people, currently estimated to be close to 690 million, could increase by up to 132 million by the end of the year (Keelan Beirne et al., 2020). Also these have cause a great effect on emotion of people around the world. In this tense situation many social connections reflect the emotions of people (de las Heras-Pedrosa C et al., 2020).

This pandemic has brought a great impact on employment due to world-wide lockdowns. Job losses for Covid-19 situation will affect family incomes and the public finances. It is a matter of concern that there are 600,000 job losses which can cause around 400,000 families a fall in income by more than 20 per cent in the absence of policy changes, with proportionately is a larger losses for those in higher income families in Ireland (Keelan Beirne et al., 2020) . Not only Ireland but the whole world shows that starting on March 13 the expected economic loss due to the corona outbreak increased sharply. The increase is from an average value of zero to an average value of about 5 percent (Dietrich et al., 2020). Thus this is an important factor to note that a pandemic is causing such a vast impact on the economy and employment of people. Along with this the daily news about job loss, disinvestment, and rapid decrease in salaries is one of the causes for man to fear about their own job sustainability. The thought of losing a source of income is leading to depression and other health related issues. Thus in this paper the authors studies about the employment sentiments in this Covid-19 situation through Sentiment Analysis Tools. The study is to review the amount of negative sentiments that a news article might contain in the context of employment. This can help journalists to maintain positivity in the articles so that human can cope up with these difficult situations.

Sentiment Analysis is also known as opinion mining or emotion in AI. It is an advanced technique that uses natural language processing, text analysis, computational linguistics, and biometrics to systematically identify, extract, quantify, and study affective states and subjective information (Walaa Medhat et al., 2014). Sentiment analysis is widely applied to study reviews and survey responses, online and social media. It helps in marketing and predicting user demand based on sentiment of user, improving product services etc. It has a great impact on the stock market (Ronen Feldman, 2013).

Newspapers apply unequal space on the different sides of an issue, which may lead to unbalanced news (Valdeavilla et al., 2019). Here the authors use Sentiment Analysis on news articles (Alexandra Balahur et al., 2010) and twitter tweet texts. They focus on news and tweet texts related to employment, unemployment, jobs and disinvestment during the first seven months of 2020 affected with the pandemic COVID-19. In these months the world has seen many ups and downs that affected the employed people in many ways. Thus they consider the news and tweets during this period as this would portray such a picture and they indeed found this change through our sentiment analysis.

Complete Article List

Search this Journal:
Reset
Volume 15: 1 Issue (2024): Forthcoming, Available for Pre-Order
Volume 14: 4 Issues (2022): 1 Released, 3 Forthcoming
Volume 13: 4 Issues (2021)
Volume 12: 4 Issues (2020)
Volume 11: 4 Issues (2019)
Volume 10: 4 Issues (2018)
Volume 9: 4 Issues (2017)
Volume 8: 4 Issues (2016)
Volume 7: 4 Issues (2015)
Volume 6: 4 Issues (2014)
Volume 5: 4 Issues (2013)
Volume 4: 4 Issues (2012)
Volume 3: 4 Issues (2011)
Volume 2: 4 Issues (2010)
Volume 1: 4 Issues (2009)
View Complete Journal Contents Listing