Social Network Analysis of COVID-19 Sentiments: Application of Artificial Intelligence

Hung, Man; Lauren, Evelyn; Hon, Eric S.; Birmingham, Wendy C.; Xu, Julie; Su, Sharon; Hon, Shirley D.; Park, Jungweon; Dang, Peter; Lipsky, Martin S.

doi:10.2196/22590

Cited by 214 publications

(163 citation statements)

References 34 publications

Supporting

Mentioning

123

Contrasting

Unclassified

Order By: Relevance

“…After studying the topics obtained by latent Dirichlet allocation topic modeling on Twitter text data, Abd-Alrazaq et al [10] identified the sentiments of four major topics and 12 subtopics, and showed that all topics were positive except for two (ie, death and racial discrimination). Similarly, Hung et al [11] adopted the Valence Aware Dictionary and Emotional Reasoner (VADER) model to analyze the sentiments expressed in user tweets and found that positive, neutral, and negative emotions accounted for 48.2%, 20.7%, and 31.1% of the tweets, respectively.…”

Section: Literature Reviewsmentioning

confidence: 99%

Understanding Concerns, Sentiments, and Disparities Among Population Groups During the COVID-19 Pandemic Via Twitter Data Mining: Large-scale Cross-sectional Study

Zhang¹,

Li²,

Hu³

2021

J Med Internet Res

View full text Add to dashboard Cite

Background Since the beginning of the COVID-19 pandemic in late 2019, its far-reaching impacts have been witnessed globally across all aspects of human life, such as health, economy, politics, and education. Such widely penetrating impacts cast significant and profound burdens on all population groups, incurring varied concerns and sentiments among them. Objective This study aims to identify the concerns, sentiments, and disparities of various population groups during the COVID-19 pandemic through a cross-sectional study conducted via large-scale Twitter data mining infoveillance. Methods This study consisted of three steps: first, tweets posted during the pandemic were collected and preprocessed on a large scale; second, the key population attributes, concerns, sentiments, and emotions were extracted via a collection of natural language processing procedures; third, multiple analyses were conducted to reveal concerns, sentiments, and disparities among population groups during the pandemic. Overall, this study implemented a quick, effective, and economical approach for analyzing population-level disparities during a public health event. The source code developed in this study was released for free public use at GitHub. Results A total of 1,015,655 original English tweets posted from August 7 to 12, 2020, were acquired and analyzed to obtain the following results. Organizations were significantly more concerned about COVID-19 (odds ratio [OR] 3.48, 95% CI 3.39-3.58) and expressed more fear and depression emotions than individuals. Females were less concerned about COVID-19 (OR 0.73, 95% CI 0.71-0.75) and expressed less fear and depression emotions than males. Among all age groups (ie, ≤18, 19-29, 30-39, and ≥40 years of age), the attention ORs of COVID-19 fear and depression increased significantly with age. It is worth noting that not all females paid less attention to COVID-19 than males. In the age group of 40 years or older, females were more concerned than males, especially regarding the economic and education topics. In addition, males 40 years or older and 18 years or younger were the least positive. Lastly, in all sentiment analyses, the sentiment polarities regarding political topics were always the lowest among the five topics of concern across all population groups. Conclusions Through large-scale Twitter data mining, this study revealed that meaningful differences regarding concerns and sentiments about COVID-19-related topics existed among population groups during the study period. Therefore, specialized and varied attention and support are needed for different population groups. In addition, the efficient analysis method implemented by our publicly released code can be utilized to dynamically track the evolution of each population group during the pandemic or any other major event for better informed public health research and interventions.

show abstract

Section: Literature Reviewsmentioning

confidence: 99%

Understanding Concerns, Sentiments, and Disparities Among Population Groups During the COVID-19 Pandemic Via Twitter Data Mining: Large-scale Cross-sectional Study

Zhang¹,

Li²,

Hu³

2021

J Med Internet Res

View full text Add to dashboard Cite

show abstract

“…Prevention measures, such as quarantine and travel bans, limited individuals’ freedom, thus further raising people’s negative emotions [ 28 , 29 ]. Health-unrelated factors like the economic and political impact, media coverage, and government responses also served as drivers of expressions of emotion [ 30 , 31 ]. However, it is worth noting that during public health emergencies, if there is no better or more convenient offline way to vent emotions, it is expected that people will turn to social media [ 1 , 2 , 3 , 32 , 33 ].…”

Section: Literaturementioning

confidence: 99%

Social Bots’ Sentiment Engagement in Health Emergencies: A Topic-Based Analysis of the COVID-19 Pandemic Discussions on Twitter

Shi

Liu

Yang

et al. 2020

IJERPH

View full text Add to dashboard Cite

During the COVID-19 pandemic, when individuals were confronted with social distancing, social media served as a significant platform for expressing feelings and seeking emotional support. However, a group of automated actors known as social bots have been found to coexist with human users in discussions regarding the coronavirus crisis, which may pose threats to public health. To figure out how these actors distorted public opinion and sentiment expressions in the outbreak, this study selected three critical timepoints in the development of the pandemic and conducted a topic-based sentiment analysis for bot-generated and human-generated tweets. The findings show that suspected social bots contributed to as much as 9.27% of COVID-19 discussions on Twitter. Social bots and humans shared a similar trend on sentiment polarity—positive or negative—for almost all topics. For the most negative topics, social bots were even more negative than humans. Their sentiment expressions were weaker than those of humans for most topics, except for COVID-19 in the US and the healthcare system. In most cases, social bots were more likely to actively amplify humans’ emotions, rather than to trigger humans’ amplification. In discussions of COVID-19 in the US, social bots managed to trigger bot-to-human anger transmission. Although these automated accounts expressed more sadness towards health risks, they failed to pass sadness to humans.

show abstract

“…Hung at al. [70] also applied machine learning methods to analyze data collected from Twitter including to identify the social network's dominant topics and whether the tweets expressed positive, neutral, or negative sentiments. They identi ed 5 main themes including: health care environment, emotional support, business economy, social change, and psychological stress.…”

Section: Discussionmentioning

confidence: 99%

Tracking Discussions of Complementary, Alternative, and Integrative Medicine in the Context of the COVID-19 Pandemic: A Month-by-Month Sentiment Analysis of Twitter Data

Abdelkader

Lokker

2021

Preprint

View full text Add to dashboard Cite

Background Coronavirus disease 2019 (COVID-19) is a novel infectious disease caused by severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2). Despite the paucity of evidence, various complementary, alternative and integrative medicines (CAIMs) have been being touted as both preventative and curative. We conducted sentiment and emotion analysis with the intent of understanding CAIM content related to COVID-19 being generated on Twitter across 9 months. Methods Tweets relating to CAIM and COVID-19 were extracted from the George Washington University Libraries Dataverse Coronavirus tweets dataset from March 03-November 30, 2020. We trained and tested a machine learning classifier using a large, pre-labelled Twitter dataset, which was applied to predict the sentiment of each CAIM-related tweet, and we used a natural language processing package to identify the emotions based on the words contained in the tweets. Results Our dataset included 28713 English-language Tweets. The number of CAIM-related tweets during the study period peaked in May 2020, then dropped off sharply over the summer; the fewest CAIM-related tweets were collected during August 2020 and remained low for the remainder of the collection period. Most tweets (n = 15612, 54%) were classified as positive, 31% were neutral (n = 8803) and 15% were classified as negative (n = 4298). The most frequent emotions expressed across tweets were trust, followed by fear, while surprise and disgust were the least frequent. Though volume of tweets decreased over the 9 months of the study, the expressed sentiments and emotions remained constant. Conclusion The results of this sentiment analysis enabled us to establish key CAIMs being discussed at the intersection of COVID-19 across a 9-month period on Twitter. Overall, the majority of our subset of tweets were positive, as were the emotions associated with the words found within them. This may be interpreted as public support for CAIM, however, further qualitative investigation is warranted. Such future directions may be used to combat misinformation and improve public health strategies surrounding the use of social media information.

show abstract

Social Network Analysis of COVID-19 Sentiments: Application of Artificial Intelligence

Cited by 214 publications

References 34 publications

Understanding Concerns, Sentiments, and Disparities Among Population Groups During the COVID-19 Pandemic Via Twitter Data Mining: Large-scale Cross-sectional Study

Understanding Concerns, Sentiments, and Disparities Among Population Groups During the COVID-19 Pandemic Via Twitter Data Mining: Large-scale Cross-sectional Study

Social Bots’ Sentiment Engagement in Health Emergencies: A Topic-Based Analysis of the COVID-19 Pandemic Discussions on Twitter

Tracking Discussions of Complementary, Alternative, and Integrative Medicine in the Context of the COVID-19 Pandemic: A Month-by-Month Sentiment Analysis of Twitter Data

Contact Info

Product

Resources

About