This document summarizes several research papers that used social network analysis on Twitter data related to COVID-19. The papers analyzed hashtags, retweets, mentions and conversations to understand public debates and information spread about topics like conspiracy theories, medical news, and public responses in different countries. The studies identified influential users, common discussions, and how social media could provide insights into managing pandemic situations.
1. CS322 Network Analysis
Answers:
Introduction
Interpersonal communication has evolved dramatically since the emergence of the internet
and relevant social networks and platforms such as Twitter, Facebook, Instagram, and many
others. Furthermore, this has resulted in a significant shift in the way content is transmitted
to consumers. User-generated material flourishes on social networking networks. This
particular paper is based upon the literature survey associated with the utilization of social
network analysis on Twitter data to find out variable insights regarding the most relevant
topic of Covid-19. The coronavirus disease (COVID-19) virus outbreak sparked widespread
debate. Organizations, communities, and people can all benefit from knowing these debates
as they attempt to manage the pandemic. The objectives of this paper are to look into
COVID-19-related comments on Twitter and how the paradigms of the social network are
surveyed by various researchers.
Literature Review
Several research has used Twitter data connected to the COVID-19 epidemic to do social
network analysis. A test case (Gruzd 2020, 3) used social network analysis methods to
investigate the spread of information of the #FilmYourHospital hashtag to see if it was
assisted by hackers or collaboration between Twitter accounts. Another research (Ahmed et
al. 2020, 1) analyzed tweets with the #5GCoronavirus tag from March 27, 2020, and April 4,
2020, to better comprehend the dynamics of the 5G COVID-19 conspiracy hypothesis and
solutions for dealing with it. The data transfer channels and headlines habits of COVID-19
on Twitter were investigated using network analysis in provincial research (Park et al.
2020, 1), conducted in South Korea.
Considering the significance of knowing public response to COVID-19, there are still gaps in
knowledge about COVID-19-related subjects. To fill this gap, researchers (Hung et al. 2020,
2) used a social network analysis of Twitter to look at social networking medium debates
about COVID-19 and social feelings about COVID-19-related topics. Tweets authored in
dialects different than English or even with geographical locations outside of the United
States were omitted from the research. To find suitable terms for the Twitter query, a
2. customized Delphi approach was employed. The writers looked over relevant academic
publications and courses in particular to find prospective keywords. These phrases were
then distributed to the other researchers for criticism and to request more terms to
improve the research results.
Another author (Ahmed et al. 2020, 3), mentioned their research and findings related to the
use of social network analysis to understand the common discussions and relevant topics
initiated by them on social media platforms. The researchers collected the data from
Twitter by exploiting the keyword “mask”. After performing the data collection procedure,
they utilized the software NodeXL, for conducting the pertinent social network analysis of
the extracted information and the data. The NodeXL software utilizes the Search Application
Process Interface (API). Moreover, according to the opinion of Ahmed et al. (2020, 5),
influential participants could be anonymized through NodeXL, but by providing a brief
demonstration of the accounts in line with their previous research which they did.
Similar use of the NodeXl was also conducted by another author to highlight the specific
relationship between the in-degree centrality with the number of followers depending on
all the participants in Twitter explored for their study. This particular study by Yum (2020,
2) particularly exploited the word cloud analysis for visualizing the interests and topics of
people for COVID-19. The author also believed that this article was among the first ones
which were based on the multitude of SNAs for Twitter. This specific study was focused on
the scenarios in the U.S. The amount of indegree centrality implies that President Trump is
by far the most effective communication node amongst some of the main participants,
according to the study. President Trump's in-degree centrality is equivalent to the total of
the best two & list of top important players, indicating that people's rights are significantly
focused on his behavior concerning the US corona situation.
Subsequently, the research associated with the evaluation of Twitter data for collecting
valuable information regarding the pandemic was also carried out by (Abd-Alrazaq et al.
2020, 3). The primary aim of their research looked to identify the most important topics
posted by the users of the respective social media platform and how effective they are in
terms of managing the situation initiated by the pandemic. The authors leveraged a range of
contraptions which included Twitter’s search API, Tweepy Python library, and PostgreSQL
database). All of these tools were executed utilizing a range of pre-demonstrated phrases
like “corona, 2019n-Cov, and COVID-19”. The authors used social network analysis
techniques for extracting the metadata and analyzed the accumulated tweets utilizing the
word frequencies of unified (unigrams) and double words (bigrams).
In several professional domains, network analysis, which is based on the framework of
graph theory, is extensively employed to classify & comprehend information in a database.
Depending on the structure (topology) of chains of Tweets and retweets, social network
analysis can be utilized to find the key Twitter accounts (e.g., stakeholders) and Tweets, and
also the relationships among them, whenever performed on Tweet data (Sunmoo et al.
3. 2020, 2). Lamsal (2021, 4) mentioned the fact that on March 11, 2020, the World Health
Organization classified the COVID-19 breakout as a pandemic. Ever since the amount of
material relating to the epidemic has exploded on social networking sites. Twitter data has
already been found to be critical in the collection of situational consciousness data related
to any disaster. The authors have presented the COV19Tweets Dataset, a large-scale Twitter
database containing over 310 million COVID-19-specific English-language messages and
emotion ratings.
Conclusion
Network analysis aids in filling in the gaps of what is occurring in the respective location be
it within a firm or an overall issue affecting the world, in a white space. Uncertain factors,
actions, and information that occur in unconnected locations are referred to as white space.
The bigger a firm becomes, the more probable it is that various groups or divisions will be
isolated from one another. While understanding how that dysconnectivity is influencing the
organization may not have been practically essential from an operating one, social network
analysis can help. In context to the benefits of Social Network Analysis, the above-
mentioned literature surveyed analyzed how the features of SNA can assist the legislative
bodies, authorities, and business organizations as well understand the trends related to the
pandemic based on the data prevailed from popular social media platform Tweeter.
References
Abd-Alrazaq, Alaa, Dari Alhuwail, Mowafa Househ, Mounir Hamdi, and Zubair Shah. "Top
concerns of tweeters during the COVID-19 pandemic: infoveillance study." Journal of
medical Internet research 22, no. 4 (2020): e19016.
Ahmed, Wasim, Josep Vidal-Alaball, Francesc Lopez Segui, and Pedro A. Moreno-Sánchez. "A
social network analysis of tweets related to masks during the COVID-19
pandemic." International Journal of Environmental Research and Public Health 17, no. 21
(2020): 8235.
Ahmed, Wasim, Josep Vidal-Alaball, Joseph Downing, and Francesc López Seguí. "COVID-19
and the 5G conspiracy theory: social network analysis of Twitter data." Journal of medical
internet research 22, no. 5 (2020): e19458.
Gruzd, Anatoliy, and Philip Mai. "Going viral: How a single tweet spawned a COVID-19
conspiracy theory on Twitter." Big Data & Society 7, no. 2 (2020): 2053951720938405.
Hung, Man, Evelyn Lauren, Eric S. Hon, Wendy C. Birmingham, Julie Xu, Sharon Su, Shirley D.
Hon, Jungweon Park, Peter Dang, and Martin S. Lipsky. "Social network analysis of COVID-
19 sentiments: Application of artificial intelligence." Journal of medical Internet research 22,
no. 8 (2020): e22590.
4. Lamsal, Rabindra. "Design and analysis of a large-scale COVID-19 tweets dataset." Applied
Intelligence 51, no. 5 (2021): 2790-2804.
Park, Han Woo, Sejung Park, and Miyoung Chong. "Conversations and medical news frames
on twitter: Infodemiological study on covid-19 in south korea." Journal of medical internet
research 22, no. 5 (2020): e18897.
Sunmoo, Y. O. O. N., Michelle Odlum, Peter Broadwell, Nicole Davis, C. H. O. Hwayoug, D. E. N.
G. Nanyi, Maria Patrao, Deborah Schauer, Michael E. Bales, and Carmela Alcantara.
"Application of social network analysis of COVID-19 related tweets mentioning cannabis
and opioids to gain insights for drug abuse research." Studies in health technology and
informatics 272 (2020): 5.
Yum, Seungil. "Social network analysis for coronavirus (COVID?19) in the United
States." Social Science Quarterly 101, no. 4 (2020): 1642-1647.