scholarly journals COVID-19 vaccination hesitancy, misinformation and conspiracy theories on social media: A content analysis of Twitter data

2020 ◽  
Author(s):  
Tasmiah Nuzhath ◽  
Samia Tasnim ◽  
Rahul Kumar Sanjwal ◽  
Nusrat Fahmida Trisha ◽  
Mariya Rahman ◽  
...  
Keyword(s):  
Social Media ◽  
Large Scale ◽  
Latent Dirichlet Allocation ◽  
Vaccine Hesitancy ◽  
Preventive Strategy ◽  
Conspiracy Theories ◽  
Mortality And Morbidity ◽  
Communication Plan ◽  
Twitter Data ◽  
Social Media Platforms

Background: The coronavirus disease (COVID-19) pandemic has caused a significant burden of mortality and morbidity. A vaccine will be the most effective global preventive strategy to end the pandemic. Studies have maintained that exposure to negative sentiments related to vaccination on social media increase vaccine hesitancy and refusal. Despite the influence social media has on vaccination behavior, there is a lack of studies exploring the public's exposure to misinformation, conspiracy theories, and concerns on Twitter regarding a potential COVID-19 vaccination. Objective: The study aims to identify the major thematic areas about a potential COVID-19 vaccination based on the contents of Twitter data. Method: We retrieved 1,286,659 publicly available tweets posted within the timeline of July 19, 2020, to August 19, 2020, leveraging the Twint package. Following the extraction, we used Latent Dirichlet Allocation for topic modelling and identified 20 topics discussed in the tweets. We selected 4,868 tweets with the highest probability of belonging in the specific cluster and manually labeled as positive, negative, neutral, or irrelevant. The negative tweets were further assigned to a theme and subtheme based on the contentResult: The negative tweets were further categorized into 7 major themes: "safety and effectiveness,” "misinformation,” "conspiracy theories,” "mistrust of scientists and governments,” "lack of intent to get a COVID-19 vaccine,” "freedom of choice," and "religious beliefs. Negative tweets predominantly consisted of misleading statements (n=424) that immunization against coronavirus is unnecessary as the survival rate is high. The second most prevalent theme to emerge was tweets constituting safety and effectiveness related concerns (n=276) regarding the side effects of a potential vaccine developed at an unprecedented speed. Conclusion: Our findings suggest a need to formulate a large-scale vaccine communication plan that will address the safety concerns and debunk the misinformation and conspiracy theories spreading across social media platforms, increasing the public's acceptance of a COVID-19 vaccination.

Vaccine-Related Content, Dynamics, and Conspiracy Theories in External Links Shared in Twitter COVID-19 Conversations: A Computational Analysis (Preprint)

2021 ◽  
Author(s):  
Iain Cruickshank ◽  
Tamar Ginossar ◽  
Jason Sulskis ◽  
Elena Zheleva ◽  
Tanya Berger-Wolf
Keyword(s):  
Social Media ◽  
Latent Dirichlet Allocation ◽  
Topic Model ◽  
Communication Strategy ◽  
Vaccine Hesitancy ◽  
Traditional Media ◽  
Conspiracy Theories ◽  
Wide Range ◽  
Social Media Platforms ◽  
Youtube Videos

BACKGROUND The onset of the COVID-19 pandemic and the consequent “infodemic” that ensued highlighted the role that social media play in increasing vaccine hesitancy. Despite the efforts to curtail the spread of misinformation, the anti-vaccination movement continues to use Twitter and other social media platforms to advance its messages. Although users typically engage with different social media platforms, research on vaccination discourse typically focused on single platforms. Understanding the content and dynamics of external content shared on vaccine-related conversations on Twitter during the COVID-19 pandemic can shed light on the use of different sources, including traditional media and social media by the anti-vaccination movement. In particular, examining how YouTube videos are shared within vaccination-related tweets is important in understanding the spread of anti-vaccination narratives. OBJECTIVE informed by agenda-setting theory, this study aimed to use machine-learning to understand the content and dynamics of external websites shared in vaccines-related tweets posted in COVID-19 conversations on Twitter. METHODS We screened around 5 million tweets posted to COVID-19 related conversations to include tweets that discussed vaccination. We then identified external content, including the most tweeted web domains and URLs within these tweets and the number of days they were shared. The topics and dynamics of tweeted YouTube videos were further analyzed by using Latent Dirichlet Allocation to topic-model the transcripts of the YouTube videos, and by independent coders. RESULTS of 841,896 vaccination-related tweets identified, 128,408 (22.1%) included external content. A wide range of external websites were shared. The 20 most tweeted websites constituted 10.9% of the shared websites and were typically shared for only 2-3 days within a one-month period. Traditional media constituted the majority of these 20 most tweeted URLs. Content of YouTube links shared had both the greatest number of unique URLs for any given URL domain and was the most tweeted domain over time. The majority (n=15) of the 20 most tweeted videos opposed vaccinations and featured conspiracy theories. Analysis of the transcripts of 1,280 YouTube videos shared indicated high frequency of conspiracy theories. CONCLUSIONS Our study reveals that sharing URLs over Twitter is a common communication strategy. Whereas shared URLs overall demonstrated a strong presence of legacy media organizations, YouTube videos were used to spread anti-vaccination messages. Produced by individuals or by foreign governments, these videos emerged as a major driver for sharing vaccine-related conspiracy theories. Future interventions should take into account cross-platform use to counteract this misinformation.

Crowdsourcing Incident Information for Emergency Response using Open Data Sources in Smart Cities

2018 ◽  
Vol 2672 (1) ◽  
pp. 198-208 ◽  
Author(s):  
Fan Zuo ◽  
Abdullah Kurkcu ◽  
Kaan Ozbay ◽  
Jingqin Gao
Keyword(s):  
Social Media ◽  
Prior Knowledge ◽  
Emergency Response ◽  
Large Scale ◽  
Latent Dirichlet Allocation ◽  
Smart Cities ◽  
Hurricane Sandy ◽  
Support Vector ◽  
Twitter Data ◽  
Emergency Events

Emergency events affect human security and safety as well as the integrity of the local infrastructure. Emergency response officials are required to make decisions using limited information and time. During emergency events, people post updates to social media networks, such as tweets, containing information about their status, help requests, incident reports, and other useful information. In this research project, the Latent Dirichlet Allocation (LDA) model is used to automatically classify incident-related tweets and incident types using Twitter data. Unlike the previous social media information models proposed in the related literature, the LDA is an unsupervised learning model which can be utilized directly without prior knowledge and preparation for data in order to save time during emergencies. Twitter data including messages and geolocation information during two recent events in New York City, the Chelsea explosion and Hurricane Sandy, are used as two case studies to test the accuracy of the LDA model for extracting incident-related tweets and labeling them by incident type. Results showed that the model could extract emergency events and classify them for both small and large-scale events, and the model’s hyper-parameters can be shared in a similar language environment to save model training time. Furthermore, the list of keywords generated by the model can be used as prior knowledge for emergency event classification and training of supervised classification models such as support vector machine and recurrent neural network.

scholarly journals Social Media Sharing of Articles About Measles in a European Context: Text Analysis Study (Preprint)

2021 ◽  
Author(s):  
Dominik Wawrzuta ◽  
Mariusz Jaworski ◽  
Joanna Gotlib ◽  
Mariusz Panczyk
Keyword(s):  
Social Media ◽  
Latent Dirichlet Allocation ◽  
Scientific Information ◽  
Vaccine Uptake ◽  
Vaccine Hesitancy ◽  
Effective Vaccine ◽  
Data Set ◽  
Vaccination Rates ◽  
Nature Of Information ◽  
Social Media Platforms

BACKGROUND Despite the existence of an effective vaccine, measles still threatens the health and lives of many Europeans. Notably, during the COVID-19 pandemic, measles vaccine uptake declined; as a result, after the pandemic, European countries will have to increase vaccination rates to restore the extent of vaccination coverage among the population. Because information obtained from social media are one of the main causes of vaccine hesitancy, knowledge of the nature of information pertaining to measles that is shared on social media may help create educational campaigns. OBJECTIVE In this study, we aim to define the characteristics of European news about measles shared on social media platforms (ie, Facebook, Twitter, and Pinterest) from 2017 to 2019. METHODS We downloaded and translated (into English) 10,305 articles on measles published in European Union countries. Using latent Dirichlet allocation, we identified main topics and estimated the sentiments expressed in these articles. Furthermore, we used linear regression to determine factors related to the number of times a given article was shared on social media. RESULTS We found that, in most European social media posts, measles is only discussed in the context of local European events. Articles containing educational information and describing world outbreaks appeared less frequently. The most common emotions identified from the study’s news data set were fear and trust. Yet, it was found that readers were more likely to share information on educational topics and the situation in Germany, Ukraine, Italy, and Samoa. A high amount of anger, joy, and sadness expressed within the text was also associated with a higher number of shares. CONCLUSIONS We identified which features of news articles were related to increased social media shares. We found that social media users prefer sharing educational news to sharing informational news. Appropriate emotional content can also increase the willingness of social media users to share an article. Effective media content that promotes measles vaccinations should contain educational or scientific information, as well as specific emotions (such as anger, joy, or sadness). Articles with this type of content may offer the best chance of disseminating vital messages to a broad social media audience.

scholarly journals Faster than warp speed: early attention to COVD-19 by anti-vaccine groups on Facebook

2021 ◽  
Author(s):  
Seth C Kalichman ◽  
Lisa A Eaton ◽  
Valerie A Earnshaw ◽  
Natalie Brousseau
Keyword(s):  
Social Media ◽  
Vaccine Development ◽  
Rapid Development ◽  
Development Program ◽  
Vaccine Safety ◽  
Vaccine Hesitancy ◽  
Conspiracy Theories ◽  
The Us ◽  
Us Government ◽  
Vaccine Information

Abstract Background The unprecedented rapid development of COVID-19 vaccines has faced SARS-CoV- (COVID-19) vaccine hesitancy, which is partially fueled by the misinformation and conspiracy theories propagated by anti-vaccine groups on social media. Research is needed to better understand the early COVID-19 anti-vaccine activities on social media. Methods This study chronicles the social media posts concerning COVID-19 and COVID-19 vaccines by leading anti-vaccine groups (Dr Tenpenny on Vaccines, the National Vaccine Information Center [NVIC] the Vaccination Information Network [VINE]) and Vaccine Machine in the early months of the COVID-19 pandemic (February–May 2020). Results Analysis of 2060 Facebook posts showed that anti-vaccine groups were discussing COVID-19 in the first week of February 2020 and were specifically discussing COVID-19 vaccines by mid-February 2020. COVID-19 posts by NVIC were more widely disseminated and showed greater influence than non-COVID-19 posts. Early COVID-19 posts concerned mistrust of vaccine safety and conspiracy theories. Conclusion Major anti-vaccine groups were sowing seeds of doubt on Facebook weeks before the US government launched its vaccine development program ‘Operation Warp Speed’. Early anti-vaccine misinformation campaigns outpaced public health messaging and hampered the rollout of COVID-19 vaccines.

Physical Distancing and Social Media Use in Emerging and Older Adults During COVID-19: Large Scale Cross-Sectional and Longitudinal Survey Study (Preprint)

2021 ◽  
Author(s):  
Thabo J van Woudenberg ◽  
Roy Hendrikx ◽  
Moniek Buijzen ◽  
Julia CM van Weert ◽  
Bas van den Putte ◽  
...  
Keyword(s):  
Older Adults ◽  
Social Media ◽  
Emerging Adults ◽  
Large Scale ◽  
Media Use ◽  
Longitudinal Survey ◽  
Social Media Use ◽  
Random Intercept ◽  
Social Media Platforms

BACKGROUND Although emerging adults play a role in the spread of COVID-19, they are less likely to develop severe symptoms after infection. Emerging adults’ relatively high use of social media as source of information raises concerns regarding COVID-19 related behavioral compliance (i.e., physical distancing) in this age group. OBJECTIVE Therefore, the current study investigated physical distancing in emerging adults in comparison to older adults and looked at the role of using social media for COVID-19 news and information in this regard. In addition, this study explored the relation between physical distancing and different social media platforms and sources. METHODS Secondary data of a large-scale national longitudinal survey (N = 123,848, 34.% male) between April and November 2020 were used. Participants indicated, ranging for one to eight waves, how often they were successful in keeping 1.5 meters distance on a 7-point Likert scale. Participants between 18 and 24 years old were considered young adults and older participants were identified as older adults. Also, a dummy variable was created to indicate per wave whether participants used social media for COVID-19 news and information. A subset received follow-up questions asking participants to indicate which platforms they have used and what sources of news and information they had seen on social media. All preregistered hypotheses were tested with Linear Mixed-Effects Models and Random Intercept Cross-Lagged Panel Models. RESULTS Emerging adults reported less physical distancing behaviors than older adults (b = -.08, t(86213.83) = -26.79, p < .001). Also, emerging adults were more likely to use social media for COVID-19 news and information (b = 2.48, SE = .11, Wald = 23.66, p = <.001), which mediated the association with physical distancing, but only to a small extend (indirect effect: b = -0.03, 95% CI = [-0.04; -0.02]). Opposed to our hypothesis, the longitudinal Random Intercept Cross-Lagged Panel Model showed no evidence that physical distancing was predicted by social media use of the previous wave. However, we did find evidence that using social media affected subsequent physical distancing behavior. Moreover, additional analyses showed that most social media platforms (i.e., YouTube, Facebook and Instagram) and interpersonal communication showed negative associations with physical distancing while others platforms (i.e. LinkedIn and Twitter) and Governmental messages showed no to a slightly positive associations with physical distancing. CONCLUSIONS In conclusion, we should be vigilant for physical distancing of emerging adults, but this study give no reason the to worry about the role of social media for COVID-19 news and information. However, as some social media platforms and sources showed negative associations, future studies should more carefully look into these factors to better understand the associations between social media use for news and information, and behavioral interventions in times of crisis.

A shift from science to politics : a content analysis of COVID-19 Videos on YouTube (Preprint)

2021 ◽  
Author(s):  
Chyun-Fung Shi ◽  
Matthew C So ◽  
Sophie Stelmach ◽  
Arielle Earn ◽  
David J D Earn ◽  
...  
Keyword(s):  
Public Health ◽  
Social Media ◽  
Content Analysis ◽  
Large Scale ◽  
Control Measures ◽  
Mitigation Measures ◽  
Health Campaigns ◽  
Public Attention ◽  
Conflicting Information ◽  
Social Media Platforms

BACKGROUND The COVID-19 pandemic is the first pandemic where social media platforms relayed information on a large scale, enabling an “infodemic” of conflicting information which undermined the global response to the pandemic. Understanding how the information circulated and evolved on social media platforms is essential for planning future public health campaigns. OBJECTIVE This study investigated what types of themes about COVID-19 were most viewed on YouTube during the first 8 months of the pandemic, and how COVID-19 themes progressed over this period. METHODS We analyzed top-viewed YouTube COVID-19 related videos in English from from December 1, 2019 to August 16, 2020 with an open inductive content analysis. We coded 536 videos associated with 1.1 billion views across the study period. East Asian countries were the first to report the virus, while most of the top-viewed videos in English were from the US. Videos from straight news outlets dominated the top-viewed videos throughout the outbreak, and public health authorities contributed the fewest. Although straight news was the dominant COVID-19 video source with various types of themes, its viewership per video was similar to that for entertainment news and YouTubers after March. RESULTS We found, first, that collective public attention to the COVID-19 pandemic on YouTube peaked around March 2020, before the outbreak peaked, and flattened afterwards despite a spike in worldwide cases. Second, more videos focused on prevention early on, but videos with political themes increased through time. Third, regarding prevention and control measures, masking received much less attention than lockdown and social distancing in the study period. CONCLUSIONS Our study suggests that a transition of focus from science to politics on social media intensified the COVID-19 infodemic and may have weakened mitigation measures during the first waves of the COVID-19 pandemic. It is recommended that authorities should consider co-operating with reputable social media influencers to promote health campaigns and improve health literacy. In addition, given high levels of globalization of social platforms and polarization of users, tailoring communication towards different digital communities is likely to be essential.

Customer Experience: Extracting Topics From Tweets

2021 ◽  
pp. 147078532110475
Author(s):  
Manit Mishra
Keyword(s):  
Social Media ◽  
Customer Service ◽  
Latent Dirichlet Allocation ◽  
Online Shopping ◽  
Customer Experience ◽  
Process Failure ◽  
Shopping Experience ◽  
Social Media Platforms ◽  
Media Platform ◽  
Moments Of Truth

The ubiquity of social media platforms facilitates free flow of online chatter related to customer experience. Twitter is a prominent social media platform for sharing experiences, and e-retail firms are rapidly emerging as the preferred shopping destination. This study explores customers’ online shopping experience tweets. Customers tweet about their online shopping experience based on moments of truth shaped by encounters across different touchpoints. We aggregate 25,173 such tweets related to six e-retailers tweeted over a 5-year period. Grounded on agency theory, we extract the topics underlying these customer experience tweets using unsupervised latent Dirichlet allocation. The output reveals five topics which manifest into customer experience tweets related to online shopping—ordering, customer service interaction, entertainment, service outcome failure, and service process failure. Topics extracted are validated through inter-rater agreement with human experts. The study, thus, derives topics from tweets about e-retail customer experience and thereby facilitates prioritization of decision-making pertaining to critical service encounter touchpoints.

scholarly journals Importance-Aware Learning for Neural Headline Editing

2020 ◽  
Vol 34 (05) ◽  
pp. 9282-9289
Author(s):  
Qingyang Wu ◽  
Lei Li ◽  
Hao Zhou ◽  
Ying Zeng ◽  
Zhou Yu
Keyword(s):  
Social Media ◽  
Large Scale ◽  
Network Models ◽  
Language Models ◽  
Neural Network Models ◽  
Generation Task ◽  
Social Media Platforms ◽  
Editing Process ◽  
Different Levels

Many social media news writers are not professionally trained. Therefore, social media platforms have to hire professional editors to adjust amateur headlines to attract more readers. We propose to automate this headline editing process through neural network models to provide more immediate writing support for these social media news writers. To train such a neural headline editing model, we collected a dataset which contains articles with original headlines and professionally edited headlines. However, it is expensive to collect a large number of professionally edited headlines. To solve this low-resource problem, we design an encoder-decoder model which leverages large scale pre-trained language models. We further improve the pre-trained model's quality by introducing a headline generation task as an intermediate task before the headline editing task. Also, we propose Self Importance-Aware (SIA) loss to address the different levels of editing in the dataset by down-weighting the importance of easily classified tokens and sentences. With the help of Pre-training, Adaptation, and SIA, the model learns to generate headlines in the professional editor's style. Experimental results show that our method significantly improves the quality of headline editing comparing against previous methods.

scholarly journals Classification Connection of Twitter Data using K-Means Clustering

2019 ◽  
Vol 8 (6S4) ◽  
pp. 14-22
Keyword(s):  
Social Media ◽  
Real Time ◽  
Clustering Methods ◽  
Time Analysis ◽  
Data Set ◽  
Dynamic Data ◽  
Real Time Analysis ◽  
Twitter Data ◽  
Social Media Platforms ◽  
Insight Into

The rise of social media platforms like Twitter and the increasing adoption by people in order to stay connected provide a large source of data to perform analysis based on the various trends, events and even various personalities. Such analysis also provides insight into a person’s likes and inclinations in real time independent of the data size. Several techniques have been created to retrieve such data however the most efficient technique is clustering. This paper provides an overview of the algorithms of the various clustering methods as well as looking at their efficiency in determining trending information. The clustered data may be further classified by topics for real time analysis on a large dynamic data set. In this paper, data classification is performed and analyzed for flaws followed by another classification on the same data set.

Sign in / Sign up

Export Citation Format

Share Document