Your browser doesn't support javascript.
Show: 20 | 50 | 100
Results 1 - 20 de 876
Filter
1.
Computers and Electrical Engineering ; : 108561, 2022.
Article in English | ScienceDirect | ID: covidwho-2165199

ABSTRACT

With the flare-up of the COVID-19 infection since 2020, COVID-19 has been one of the hottest topics on Twitter. Topic modeling is one of the most popular analyses, which extracts the topics from the text. This paper proposes a method to extract the most-discussed topics for 32 countries of the world. In this regard, more than five million related tweets have been studied, and a method based on content analysis is proposed to identify the exact location of each tweet. Then, by using the statistical algorithm of Latent Dirichlet Allocation, the main topics of the tweets are identified. By leveraging sentiment analysis, the topics are afterward divided into positive and negative groups, and their trends in a quarterly period are investigated for the countries under study. The outcome of the analysis of time trends shows that for most countries, the trend of negative topics is highly correlated with the number of confirmed cases of COVID-19.

2.
Research in International Business and Finance ; 64:101850, 2023.
Article in English | ScienceDirect | ID: covidwho-2165810

ABSTRACT

This study aims to examine whether the prices and returns of two cryptocurrencies, Dogecoin and Ethereum, are affected by Twitter engagement following the COVID-19 pandemic. We use the autoregressive integrated moving average with explanatory variables model to integrate the effects of investor attention and engagement on Dogecoin and Ethereum returns using data from December 31, 2020, to May 12, 2021. The results provide evidence supporting the hypothesis of a strong effect of Twitter investor engagement on Dogecoin returns;however, no potential impact is identified for Ethereum. These findings add to the growing evidence regarding the effect of social media on the cryptocurrency market and have useful implications for investors and corporate investment managers concerning investment decisions and trading strategies.

3.
Journal of Pharmaceutical Negative Results ; 13:713-722, 2022.
Article in English | EMBASE | ID: covidwho-2164814

ABSTRACT

Aim: The primary aim of this research is to increase the intensity percentage of personage traits detection to reveal the impact of coronavirus on Twitter users by utilizing machine learning classifier algorithms by comparing Novel Naive Bayes Classifier algorithm and Logistic Regression algorithm. Material(s) and Method(s): Naive Bayes Classifier algorithm with test size=10 and Logistic Regression algorithm with test size=10 was estimated several times to envision the efficiency percentage with confidence interval of 95% and G-power (value=0.8). Naive Bayes classifier compares whether a specific feature in a class is unrelated to another feature. A logistic regression model predicts the probability of an item belonging to one group or another. Results and Discussion: Naive Bayes algorithm has greater efficiency (86%) when compared to Logistic Regression efficiency (60%). The results achieved with significance value p=0.169 (p>0.05) shows that two groups are statistically insignificant. Conclusion(s): Naive Bayes Algorithm executes remarkably greater than the Logistic Regression algorithm. Copyright © 2022 Wolters Kluwer Medknow Publications. All rights reserved.

4.
Dirasat: Human and Social Sciences ; 49(5):617-630, 2022.
Article in Arabic | Scopus | ID: covidwho-2164711

ABSTRACT

The study aims to identify the extent of the study sample's interest in news coverage of health issues of the Corona pandemic, and to identify the types of persuasive solicitation that the agency used in its newsletter to educate citizens and residents about the dangers of the pandemic, and to know how the agency used in its publication of images and fees to raise awareness of the risks of the pandemic, and to calculate the numerical quantity of topics Health and social in the SPA Twitter account. To achieve the goal of the study, the survey method was adopted, and two of the five surveys were employed;the two are media survey and content analysis. The study highlighted the weakness of the efforts of the SPA news agency to raise health and social awareness among citizens and residents about the risks of the pandemic during the study period. In addition to the agency's use in its publication of many fears, emotional and mental solicitations in social topics in the SPA Twitter account, its significance was not strong enough in raising awareness of the pandemic during the study period. The study concludes that the media should push for more information that contributes strongly to refuting these rumors, and other researchers should conduct more interdisciplinary research with humanitarian and educational studies about the pandemic, and a great burden will fall on journalists and citizens through the optimal use of digital media tools that have become inevitable in spreading awareness of the risks of diseases and epidemics expected in the coming years. © 2022 DSR Publishers/The University of Jordan.

5.
Observatorio ; 16(3):34-52, 2022.
Article in Spanish | Scopus | ID: covidwho-2164352

ABSTRACT

The Covid-19 pandemic and the arrival of Disney + marked the second quarter of 2020 in the Spanish audiovisual market. Thus, the period of home confinement among the Spanish population coincided with the irruption of the new streaming service of one of the best-known and most loved brands worldwide. However, Netflix was the most consumed SVoD during this period. The objective of this research is to find out what the Californian company has done in communicative terms as a market leader and in the face of the need to adapt to the new circumstances of its audiences. The results show how Netflix Spain has integrated COVID-19 in its social media strategy in the pass between the lockdown and maximum consumption to a progressive lessening of social restrictions. The content analysis of Twitter and Instagram found 121 messages regarding pandemic (from a total of 1380). Netflix employed Twitter to connect with its audiences with humor, proximity and information, using taboos in the hardest moments, and an increased frequency of publications as the health situation improved. On the contrary, on Instagram there was no specific strategy, but imitation of the practices on Twitter and scarce references to COVID. Besides, there has been an evolution of the messages more or less parallel to the public health changes, choosing a strategy of proximity with the users, and with a communication closer to an influencer rather than a company. Copyright © 2022 (Fernández-Gómez, Martín-Quevedo, Feijoo Fernández).

6.
International Journal of Computational Economics and Econometrics ; 12(4):429-444, 2022.
Article in English | Scopus | ID: covidwho-2162614

ABSTRACT

In the last decade, social networks have increasingly been used in social sciences to monitor consumer preferences and citizens' opinion formation, as they are able to produce a massive amount of data. In this paper, we aim to collect and analyse data from Twitter posts identifying emerging patterns related to the COVID-19 outbreak and to evaluate the economic sentiment of users during the pandemic. Using the Twitter API, we collected tweets containing the term coronavirus and at least a keyword related to the economy selected from a pre-determined batch, obtaining a database of approximately two million tweets. We show that our Economic Twitter Index (ETI) is able to nowcast the current state of economic sentiment, exhibiting peaks and drops related to real-world events. Finally, we test our index and it shows a positive correlation to standard economic indicators. Copyright © 2022 Inderscience Enterprises Ltd.

7.
Journal of Consumer Health on the Internet ; 26(4):337-356, 2022.
Article in English | ProQuest Central | ID: covidwho-2160685

ABSTRACT

Objective: This study aimed to categorize and analyze the public response toward third/booster shots of COVID-19 on Twitter. Methods: We downloaded the COVID-19 vaccine booster shots related Tweets using the Twitter API. The collected Tweets were pre-processed to prepare them for analysis by (1) removing non-English language tweets, retweets, emojis, emoticons, non-printable characters, the punctuation marks, and the prepositions, (2) anonymizing the identity of the users, and (3) normalizing various forms of the same words. We used the state-of-the-art BertTopic modeling library to identify the most popular topics. Results: Of 165,048 Tweets collected, 36,908 Tweets were analyzed in this study. From these tweets, we identified 9 topics, which were about Biden administration, Pfizer & BioNTech, Moderna, Johnson & Johnson, eligibility for booster shots, side effects, Donald Trump, variants of the Novel Coronavirus, and conspiracy theory & propaganda. The mean of sentiment was positive in all topics. The lowest and highest mean of sentiments were for the Donald Trump topic (0.0097) and the Johnson & Johnson topic (0.1294), respectively. Conclusions: The topics identified in this study not only accurately reflect the contemporary COVID-19 discussion, but also the high degree of politicization in the USA. While the latter might be a result of our rejection of non-English tweets, it is reassuring to see our fully automated, unsupervised pipeline reliably extract such global features in the data at scale. We, therefore, believe that the methodology presented in this study is mature and useful for other infoveillance studies on a wide variety of topics.

8.
Disaster Med Public Health Prep ; : 1-27, 2022.
Article in English | PubMed | ID: covidwho-2160019

ABSTRACT

In our Information Technology (IT) based societies, social media play an important role in communications and social networks for COVID-19. This study explores social responses for COVID-19 in North America, which the most severe continent affected by the COVID-19 pandemic. This study employs social network analysis for Twitter among the US, Canada, and Mexico. This study finds that the three countries show different characteristics of social networks for COVID-19. For example, the Prime Minister plays the second important role in the Canada networks, whereas the presidents play the most significant role in them in the US and Mexico. WHO shows a pivotal effect on social networks of COVID-19 in Canada and the US, whereas it does not affect them in Mexico. Canada people are interested in COVID-19 apps, the US people criticize the president and administration as incompetent for COVID-19, and Mexico people search for COVID-19 cases and the pandemic in Mexico. This study shows that governments and disease experts should understand social networks and communications of social network services to develop effective COVID-19 policies according to the characteristics of their country.

9.
16th Conference of the European Chapter of the Association for Computational Linguistics (Eacl 2021) ; : 3402-3420, 2021.
Article in English | Web of Science | ID: covidwho-2156484

ABSTRACT

We describe mega-COV, a billion-scale dataset from Twitter for studying COVID-19. The dataset is diverse (covers 268 countries), longitudinal (goes as back as 2007), multilingual (comes in 100+ languages), and has a significant number of location-tagged tweets (similar to 169M tweets). We release tweet IDs from the dataset. We also develop two powerful models, one for identifying whether or not a tweet is related to the pandemic (best F-1 =97%) and another for detecting misinformation about COVID-19 (best F-1 =92%). A human annotation study reveals the utility of our models on a subset of Mega-COV. Our data and models can be useful for studying a wide host of phenomena related to the pandemic. Mega-COV and our models are publicly available.

10.
International Journal of Mental Health Promotion ; 25(1):21-29, 2023.
Article in English | Scopus | ID: covidwho-2156179

ABSTRACT

This study aimed to explore citizens’ emotional responses and issues of interest in the context of the coronavirus disease 2019 (COVID-19) pandemic. The dataset comprised 65,313 tweets with the location marked as New York State. The data collection period was four days of tweets when New York City imposed a lockdown order due to an increase in confirmed cases. Data analysis was performed using R Studio. The emotional responses in tweets were analyzed using the Bing and NRC (National Research Council Canada) dictionaries. The tweets’central issue was identified by Text Network Analysis. When tweets were classified as either positive or negative, the negative sentiment was higher. Using the NRC dictionary, eight emotional classifications were devised: “trust,” “fear,” “anticipation,” “sadness,” “anger,” “joy,” “surprise,” and “disgust.” These results indicated that citizens showed negative and trusting emotional reactions in the early days of the pandemic. Moreover, citizens showed a strong interest in overcoming and coping with other people such as social solidarity. Citizens were concerned about the confirmation of COVID-19 infection status and death. Efforts should be made to ensure citizens’ psychological stability by promptly informing them of the status of infectious disease management and the route of infection. © 2023, Tech Science Press. All rights reserved.

11.
International Journal of Electronic Healthcare ; 12(4):299-317, 2022.
Article in English | Scopus | ID: covidwho-2154325

ABSTRACT

This study explores how governments use social media for COVID-19 to communicate with the public according to government accounts by employing social network analysis for Twitter. First, this study finds that government accounts have different characteristics of key players. For instance, the US key players play an important role in the Donald Trump networks, whereas international key players play a significant role in the President of the United States (POTUS) networks. Second, Trump, POTUS, and the White House show a similar pattern, whereas the US Government reveals a unique shape for the social networks. Third, the US Government networks also exhibit unique characteristics of group networks against other government accounts. Fourth, citizens reply differently to the government accounts for the COVID-19 issue. For example, Donald Trump shows overwhelming replies over other tweeters in the Donald trump networks, whereas POTUS ranks second after Donald Trump in the POTUS networks. Copyright © 2022 Inderscience Enterprises Ltd.

12.
2022 International Conference on Edge Computing and Applications, ICECAA 2022 ; : 1559-1564, 2022.
Article in English | Scopus | ID: covidwho-2152470

ABSTRACT

Worldwide, the (COVID-19) pandemic had also affected people's daily routines. In general also during lockdown periods, people around the world use social media to express their thoughts and feelings about the epidemic which has interrupted their daily lives. There has been a huge spike in tweets about coronavirus on Twitter in a short period of time, including both positive and negative messages. As a result of the wide range of content in the tweets, the researchers have turned to sentiment analysis in order to gauge how the general public feels about COVID-19. According to the findings of this study, the best way to examine COVID-19 is to look athow people use Twitter to share theirthoughts and opinions. Sentiment categorization can be accomplished by utilising a variety of feature sets as well as classifiers in combination with the suggested approach. Tweets collected from people with COVID-19 perceptions can be used to better understand and manage the epidemic. Positive, negative, as well as neutral emotion classifications are being usedto classify tweets. In this study, Tweets containing specific information about the Coronavirus epidemic are used as sentiment analysis packages. Bidirectional Encoder Representations from Transformers (BERT) are used to identify sentiment categories, whereas the TF-IDF (term frequency-inverse document frequency) prototype is used to summarise the topics of postings. Trend analysis and qualitative methods are being used to identify negative sentiment traits. In general, when it comes to sentiment classification, the fine-tuned BERT is very accurate. In addition, the COVID-19related post features of TF-IDF themes are accurately conveyed. Coronavirus tweet sentiments are analysedusing a BERT and TF-IDF hybrid classifier. Single-sentence classification is transformedinto pair-sentence classification, which solves BERT's performance issue in text classification problems. Our evaluation measures (accuracy= 0.70;precision= 0.67;recall= 0.64;and F1-score= 0.65) are used to evaluate the effectiveness of the classifier. © 2022 IEEE.

13.
10th International Conference on Cyber and IT Service Management, CITSM 2022 ; 2022.
Article in English | Scopus | ID: covidwho-2152444

ABSTRACT

As the COVID-19 pandemic begins, the perception of online lectures according to students needs to be researched, to find out whether students have positive or negative sentiments regarding online lectures so far. Therefore, it is necessary to conduct research on sentiment analysis about online lectures taken according to student comments via tweets on the Twitter platform. The extracted tweets data will then be analyzed using machine learning to predict student sentiment about online lectures. The multilayer perceptron algorithm is used in research because it can solve non-linear problems well and is easy to implement without complicated parameter settings. However, multilayer perceptron is a supervised learning algorithm so it requires data that has been labeled/classified. So that to label the data of online lecture tweets, lexicon-based sentiment analysis is used. A total of 2,391 Indonesian-language tweets were successfully extracted. The results of the study using lexicon-based showed that as many as 63.9% gave negative sentiments towards online lectures, and 29% gave positive sentiments while the remaining 7.1% gave neutral sentiments. Meanwhile, the prediction ability of the multilayer perceptron algorithm for tweets data in this online lecture produces an accuracy of 71%. © 2022 IEEE.

14.
J Aging Stud ; 63:101076, 2022.
Article in English | PubMed | ID: covidwho-2149965

ABSTRACT

With the proliferation of social media networks, online discussions can serve as a microcosm of the greater public opinion about key issues that affect society as a whole. Online discussions have been catalyzed by the COVID-19 pandemic and have magnified challenges experienced by older adults, health care professionals, and caregivers of long-term care (LTC) residents. Our main goal was to examine how online discussions and public perceptions about LTC practices have been impacted by the COVID-19 pandemic. We conducted a content analysis of Twitter posts about LTC to understand the nature of social media discussions regarding LTC practices prior to (March to June 2019) and following the declaration of the COVID-19 pandemic (March to June 2020). We found that a much greater number of Twitter posts about LTC was shared during the COVID-19 period than in the year prior. Multiple themes emerged from the data including highlighting concerns about LTC, providing information about LTC, and interventions and ideas for improving LTC conditions. The proportion of posts linked to several of these themes changed as a function of the pandemic. Unsurprisingly, one major new issue that emerged in 2020 is that users began discussing the shortcomings of infection control during the pandemic. Our findings suggest that increased public concern offers momentum for embarking on necessary changes to improve conditions in LTC.

15.
Annals of Operations Research ; : 1-19, 2022.
Article in English | Academic Search Complete | ID: covidwho-2148821

ABSTRACT

The study illustrates an application of evidence data for performing Total Interpretive Structural Modeling (TISM). TISM is widely used to analyze the critical success factors or inhibitors and their interlinkages. This study uses learning from evidence data, specifically social media analytics, to identify the relationship between the elements. Thus, it leads to the advancement of the TISM-P methodology with evidence-based TISM (TISM-E). This study uses Twitter as a source of evidence data. Further, 2,60,297 tweets were used to illustrate the process of TISM-E. The paper demonstrates the application of TISM-E for the success of the COVID-19 vaccination drive. The pandemic effects are long-term;therefore, the hierarchical model developed shows a sustainable approach for vaccinating maximum population. Further, the framework developed will ensure the distribution efficacy of vaccines. In addition, it will aid practitioners in developing future vaccination policies. The enhanced model provides evidence for polarity (positive/negative) of relationships and can help to build propositions for theory development. The study contributes to healthcare, modeling research, and graph-theoretic literature. [ FROM AUTHOR]

16.
3rd Doctoral Symposium on Computational Intelligence, DoSCI 2022 ; 479:37-55, 2023.
Article in English | Scopus | ID: covidwho-2148650

ABSTRACT

The COVID-19 pandemic has effectively shut down the whole planet. Most countries have now suspended lockdowns or semi-lockdowns, although lockdowns still exist in many countries. The coronavirus epidemic has disrupted people's daily lives. People from all across the globe have flocked to social media to voice their thoughts and feelings on the phenomenon that has gone viral. In a very short period of time, the social networking site Twitter saw an extraordinary rise in tweets pertaining to the novel coronavirus. With the discovery of several vaccines for the virus, the new year of 2021 brought with it new hope. A global vaccine campaign is under way, and we anticipate that the world will quickly recover from this pandemic and return to normalcy. This paper is devoted to the vaccination drive's tweets. This is used to predict the attitude of tweets on vaccinations. We have taken note of how sentiment changes over time, with respect to vaccination, through the general people who tweeted. For analysis, VADER and LSTM, Z-score, have been used. Additionally, with vaccine data visualization, the most common positive and negative, all hashtags, and the source of the data have been analyzed. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

17.
Lecture Notes on Data Engineering and Communications Technologies ; 152:768-778, 2023.
Article in English | Scopus | ID: covidwho-2148636

ABSTRACT

In the era of Covid 19 pandemic, governments have imposed nationwide lockdowns which make a huge change to people daily routines. This last affect indirectly on the well-being of people’s mental health, especially the vulnerable population. And due to social media, many conversations about these phenomena occur online, especially those related to people’s emotions. Then the field of sentiment analysis is requested. In this paper, we aimed to extract correlations within this epidemic and its psychologic effects. In fact, our goal is to extract features that may improve sentiment analysis accuracy which is a crucial step to fulfill the main objective of our research: developing an intelligent recommendation system that will benefit persons, through a positive accompaniment and the early alert, in case of complex situations as mental illness. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

18.
International Conference on Information Systems and Intelligent Applications, ICISIA 2022 ; 550 LNNS:639-648, 2023.
Article in English | Scopus | ID: covidwho-2148569

ABSTRACT

Covid-19 (Corona virus) hits the world with wildness, affecting various sectors of life. The whole world has united to confront the virus, and different vaccines were developed to vaccinate the largest possible percentage as an effort to reach community immunity to limit its spread. Governments seek to measure public opinion about vaccination campaigns to improve the quality of services provided. One of the most effective ways to do this is to use artificial intelligence to sense and analyze what the public is posting on social media such as Twitter to ensure that their opinion is known without bias. The study used Twitter API to retrieve Arabic tweets then measured public acceptance of vaccination against Covid-19 disease by using sentiment analysis combined with deep learning as a technique that ensures access to people’s opinions quickly and at a very low cost. The results of this study showed that most people are having a positive opinion on the vaccination with different percentages vary from a vaccine type to another. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

19.
Pain Physician ; 25(7):E1021-E1025, 2022.
Article in English | EMBASE | ID: covidwho-2147675

ABSTRACT

Background: Approximately 70% of Americans use social media platforms, and use of specific platforms, such as Instagram, Twitter, Snapchat, and TikTok, is especially common among adults under 30. The presence of social media accounts among residency and fellowship programs in academic medicine has been used to connect with other specialties, highlight achievements and research, disseminate information to the general public, and as a recruiting tool for applicants. Objective(s): The objective of this cross-sectional study was to evaluate the social media presence, specifically on Twitter and Instagram, of the Accreditation Council for Graduate Medical Education (ACGME)-accredited Pain Medicine fellowship programs. We hypothesized that programs with more fellows were more likely to have a social media presence, as well as more content pertaining to branding for recruitment purposes. Study Design: A cross-sectional study observing the social media presence of ACGME-accredited Pain Medicine fellowship programs. Method(s): Two independent reviewers conducted searches for corresponding official pain programs and departmental accounts on Twitter and Instagram over the period of July 1, 2020 to June 31, 2021. For all social media accounts identified, number of posts (total and within the study period), followers, and date of first post were recorded. Each post was categorized as medical education, branding, or social. Result(s): Of the 111 ACGME-accredited Pain Medicine fellowship programs {AU: UC/LC?}, 4 (3.6%) had both Twitter and Instagram accounts,10 (9%) only Twitter, 7 (6.3%) only Instagram, and 90 (81.1%) had neither. A significant association between the number of fellows and the odds of having an Instagram, but not Twitter, fellowship account was found (odds ratio 1.38, 95% confidence interval [CI]: 1.02,1.88;P = 0.038). Also, a linear relationship existed between the number of followers and tweets (B coefficient 3.7, 95% CI: 3.6, 3.8;P < 0.001). Limitation(s): Limitations include that the data were collected during the COVID-19 pandemic, which may correlate to increased likelihood of social media usage. We were also limited by our ability to find all of the pain management fellowship program accounts on social media. Conclusion(s): Less than 20% of the pain fellowship programs are currently utilizing Twitter and/ or Instagram. When compared to primary anesthesiology residencies, social media presence among pain fellowships is much lower. By utilizing basic social media strategies, including image-based content posting, hashtags, and videos, programs can increase their engagement with the social media community, and increase their overall number of followers, thus expanding their potential reach to prospective applicants. Although social media can be an effective tool for branding purposes, it is vital to address the safe use of social media among all trainees. Copyright © 2022, American Society of Interventional Pain Physicians. All rights reserved.

20.
Soc Media Soc ; 8(4): 20563051221138753, 2022.
Article in English | MEDLINE | ID: covidwho-2139050

ABSTRACT

Modern politics is permeated by blame games-symbolic struggles over the blameworthiness or otherwise of various social actors. In this article, we develop a framework for identifying different strategies of blaming that protesters use on social media to criticize and delegitimize governments and political leaders. We draw on the systemic functional linguistic theory of Appraisal to distinguish between blame attributions based on negative judgments of the target's (1) capacity, such as references to their incompetence and policy failures; (2) veracity, questioning their truthfulness or honesty via references to deceitful character or dishonest acts and utterances; (3) propriety, questioning their moral standing by references to, for instance, corruption; and (4) tenacity, suggesting that the politicians are not dependable due to, for example, dithering. We add to this a further threefold distinction based on whether blaming is focused on the target's (1) bad character, (2) bad behavior, or (3) negative outcomes that the target either caused or did not prevent from happening. To illustrate the approach, we analyze a corpus of replies by Twitter users to tweets by British government ministers about two highly contentious issues, Covid-19 and Brexit, in 2020-2021. We suggest that the methodology outlined here could provide a useful avenue for systematically revealing and comparing a variety of realizations of blaming in large datasets of online conflict talk, thereby providing a more fine-grained understanding of the practices of protest and delegitimation in modern politics.

SELECTION OF CITATIONS
SEARCH DETAIL