Twitter Research Articles

Deep Learning Model for COVID-19 Sentiment Analysis on Twitter.

The COVID-19 pandemic impacted the mood of the people, and this was evident on social networks. These common user publications are a source of information to measure the population's opinion on social phenomena. In particular, the Twitter network represents a resource of great value due to the amount of information, the geographical distribution of the publications and the openness to dispose of them. This work presents a study on the feelings of the population in Mexico during one of the waves that produced the most contagion and deaths in this country. A mixed, semi-supervised approach was used, with a lexical-based data labeling technique to later bring these data to a pre-trained model of Transformers completely in Spanish. Two Spanish-language models were trained by adding to the Transformers neural network the adjustment for the sentiment analysis task specifically on COVID-19. In addition, ten other multilanguage Transformer models including the Spanish language were trained with the same data set and parameters to compare their performance. In addition, other classifiers with the same data set were used for training and testing, such as Support Vector Machines, Naive Bayes, Logistic Regression, and Decision Trees. These performances were compared with the exclusive model in Spanish based on Transformers, which had higher precision. Finally, this model was used, developed exclusively based on the Spanish language, with new data, to measure the sentiment about COVID-19 of the Twitter community in Mexico.

User Interaction with Climate Change Visualizations on Social Media (Arabic)

The present study aims to analyze the usage of pictures and other visual materials, including static or animated graphics, infographics, maps, and videos, in covering climate change issues on Instagram and Twitter. The study examines user interaction with this visual content by tracking the characteristics of users’ comments on climate change posts published on both social media platforms between October 1st, 2021 and the end of June 2022. A theoretical and interpretive framework was built around concepts of the Public Sphere and the social media engagement theory advanced by Gangi and Wasko (2016),, which allowed a number of questions to be raised, most notably: How did the studied accounts on Instagram and Twitter visually engage climate change issues? What types of pictorial and visual materials were used to address climate change issues on both platforms? And what were the characteristics of users’ comments on this visual content? The results of this study show great diversity in modes of visual engagement with climate change issues. They demonstrate that realistic and on-site images were most used, alongside videos, live broadcasts, and 3D images, and that the users of both social media platforms extensively interact with graphic materials that express local climate issues that pose a direct threat to their lives. The study also reveals that the users’ comments on the climate change posts published on the Egyptian Ministry of Environment’s Twitter account were characterized by their critical, aggressive, and satirical tone, whereas the users’ comments on the posts published on the UK COP26’s Presidency Twitter account were characterized by their ability to create a public space and an arena for debate, criticism, and sharing of views. Likewise, the comments on the official Instagram account of the United Nations Climate Change Authority engaged in serious discussions, proposals, and solutions to various climate and environmental problems.

Effect of Non-pharmaceutical Interventions on COVID-19 in Rwanda: An Observational Study

BackgroundOn 11 March 2020, COVID-19 was declared as a pandemic by the World Health Organization (WHO). The first case was identified in Rwanda on 24 March 2020. Three waves of COVID-19 outbreak have been observed since the identification of the first case in Rwanda. During the COVID-19 epidemic, the country of Rwanda has implemented many Non-Pharmaceutical Interventions (NPIs) that appear to be effective. However, a study was needed to investigate the effect of non-pharmaceutical interventions applied in Rwanda to guide ongoing and future responses to epidemics of this emerging disease across the World.MethodsA quantitative observational study was conducted by conducting analysis of COVID-19 cases reported daily in Rwanda from 24 March 2020 to 21 November 2021. Data used were obtained from the official Twitter account of Ministry Health and the website of Rwanda Biomedical Center. Frequencies of COVID-19 cases and incidence rates were calculated, and to determine the effect of non-pharmaceutical interventions on changes in COVID-19 cases an interrupted time series analysis was used.ResultsRwanda has experienced three waves of COVID-19 outbreak from March 2020 to November 2021. The major NPIs applied in Rwanda included lockdowns, movement restriction among districts and Kigali City, and curfews. Of 100,217 COVID-19 confirmed cases as of 21 November 2021, the majority were female 51,671 (52%) and 25,713 (26%) were in the age group of 30–39, and 1866 (1%) were imported cases. The case fatality rate was high among men (n = 724/48,546; 1.5%), age > 80 (n = 309/1866; 17%) and local cases (n = 1340/98,846; 1.4%). The interrupted time series analysis revealed that during the first wave NPIs decreased the number of COVID-19 cases by 64 cases per week. NPIs applied in the second wave decreased COVID-19 cases by 103 per week after implementation, while in the third wave after NPIs implementation, a significant decrease of 459 cases per week was observed.ConclusionThe early implementation of lockdown, restriction of movements and putting in place curfews may reduce the transmission of COVID-19 across the country. The NPIs implemented in Rwanda appear to be effectively containing the COVID-19 outbreak. Additionally, setting up the NPIs early is important to prevent further spread of the virus.

Personality Analysis by Tweet Mining

Social Media addiction is becoming a Commonplace. A user gets deeply involve with an application or website that he share it thoughts , ideas and viewpoints on these platforms more comfortably then communicating with an people face to face . By text mining these viewpoint and thoughts from social Media psychological profiling can b done to improve user experience & personality assessment .The aim is to exhibits the construct validation framework for Personality Analysis using machine learning approaches like Term Frequency-Inverse Document Frequency (TF-IDF) SVM. We put forward the methodology by which user’s personality can be analyzed using publicly available information on user’s personal Twitter account using the Myers_Briggs Type Indicator (MBTI). This study will contribute & help in many ways such as customization of Content displayed and product list , Recruitment and Information Retrieval.

Deliberative democracy and the digital public sphere: Asymmetrical fragmentation as a political not a technological problem

Deliberative democracy and the digital public sphere: Asymmetrical fragmentation as a political not a technological problem

Abstract Number ‐ 203: #BEFASTChallenge: Social Media Dance Campaign for Stroke Symptoms Awareness

Introduction Public stroke education campaigns have traditionally utilized mass media. We hypothesized that a worldwide stroke awareness social media campaign, utilizing dance videos to express the BE‐FAST acronym for stroke signs and symptoms, could reach a large audience at a low cost. Methods Mission Thrombectomy 2020+ officially launched the #BEFASTChallenge, a Social Media (SoMe) public stroke educational campaign, on May 15, 2022, World Stroke Thrombectomy Day, after an internal “lead‐in” phase starting the first week of May 2022. The campaign was volunteer designed and implemented. The public and their followers were encouraged to post a video of their dance depicting each letter of BE‐FAST, tag the post with #BEFASTChallenge, and nominate others to participate. We tracked the SoMe posts from May 4th through July 13, 2022, on Facebook (FB), Twitter (TW), and Instagram (IG) platforms by searching #BEFASTChallenge on each SoMe site. We ascertained campaign adoption, public reach, and interaction by measuring original posts, views, likes, retweets, shares, and comments. Results There were 4 countries represented in the original posts on SoMe with the vast majority being from the US. The first post was on May 4, and the last was on July 13 (71 days), resulting in a daily average of 0.55 posts. The largest number of posts occurred on the launch date (16 posts). There were 39 original posts, which accumulated 170 retweets, 44 quote tweets, 755 likes, 32 comments, and 14 shares. The videos had 13,821views (Table 1). Conclusions We report that the preliminary analysis of a volunteer‐driven SoMe public stroke campaign utilizing dance to express stroke symptoms demonstrates feasibility, reaching a modest audience directly with good interaction. A similar professionally implemented SoMe campaign could lead to increased and more sustained user engagement to raise public stroke symptom awareness.

THE IMPACT OF TWITTER ON FIRM VALUE

ABSTRACT Twitter is a leading firm in social media information with important implications across various spheres ranging from politics to the capital markets. This study examines the impact of Twitter on firm value. We analyze the returns on publicly traded stocks of firms that start to use Twitter. We find that the Return on Twitter (ROT) initiation events are positive and statistically significant for latter initiations. We find evidence that the positive impact of using Twitter accrued to companies that adopted Twitter use more recently indicating that the value of using Twitter became more known to investors as Twitter developed. There are differing impacts on firm value from initiating a Twitter account for companies in different industries. Furthermore, we show that abnormal returns are far more significantly negative for smaller firms than larger firms when sorted by their size. Keywords Twitter, Event Study, Cumulative Abnormal Return, Firm Value

Interactive Governmental Communication Promoting Participatory Citizen Engagement in Health Crisis Events - Evidence from India

During crises events, governments attempt to diminish the situational uncertainty and distrust among citizens and control their emotional response. Drawing on the merits of interactive communication in the crisis times and potential of social media platforms, we empirically investigated how Government of India (Gol) used Twitter to enable participatory citizen engagement during the nationwide lockdown (March 24 – May 31, 2020) to deal with COVID-19. In this study we used social media analytics to examine, how interactive governmental communication relates to some theoretically relevant factors such as participatory citizens’ engagement, media richness, situational uncertainty, level of distrust and citizens’ emotions fostered by pandemic crisis. The analysis based on data extracted from official Twitter handles of Gol for the lockdown period showed that the participatory citizen engagement in interactive governmental communication effectively promotes citizens’ positive emotions and reduces levels of situational uncertainty and distrust. But media richness should not be overemphasized, as it may attract undesirable outcomes.

An Analysis of Crypto Scams during the Covid-19 Pandemic: 2020-2022

Blockchain and cryptocurrency adoption has increased significantly since the start of the Covid-19 pandemic. This adoption rate has overtaken the Internet adoption rate in the 90s and early 2000s, but as a result, the instances of crypto scams have also increased. The types of crypto scams reported are typically giveaway scams, rug pulls, phishing scams, impersonation scams, Ponzi schemes as well as pump and dumps. The US Federal Trade Commission (FTC) reported that in May 2021 the number of crypto scams were twelve times higher than in 2020, and the total loss increased by almost 1000%. The FTC also reported that Americans have lost more than $80 million due to cryptocurrency investment scams from October 2019 to October 2020, with victims between the ages of 20 and 39 represented 44% of the reported cases. Social Media has become the go-to place for scammers where attackers hack pre-existing profiles and ask targets’ contacts for payments in cryptocurrency. In 2020, both Joe Biden and Bill Gates’ Twitter accounts were hacked where the hacker posted tweets promising that for all payments sent to a specified address, double the amount will be returned, and this case of fraud was responsible for $100,000 in losses. A similar scheme using Elon Musk’s Twitter account resulted in losses of nearly $2 million. This paper analyses the most significant blockchain and cryptocurrency scams since the start of the Covid-19 pandemic, with the aim of raising awareness and contributing to protection against attacks. Even though the blockchain is a revolutionary technology with numerous benefits, it also poses an international crisis that cannot be ignored.

Redrawing the lines of veracity in the Sharpiegate affair: “Pre-truth” claims in a Post-truth order

ABSTRACT Looking back at the 2019 Sharpiegate affair, the article investigates the articulation of “pre-truth,” which became evident when a willful ambivalence toward factual evidence dovetailed with a juxtaposition of provisional, future-oriented truth claims. In general, the maneuver works by taking predictive statements from the past and characterizing them as accurate from the standpoint of the present even when superseded by subsequent evidence. The notion of “pre-truth” adds nuance to conceptions of post-truth by looking more closely at the intertwining of veracity and temporality. Drawing lessons from the Sharpiegate affair, we show how the @realDonaldTrump Twitter account was employed to distort meteorological forecasts and challenge journalism’s privilege to premediate events as they unfold. In turn, legacy media organizations struggled to ward off these attacks. We investigate the snowballing U.S. news story around the affair using tweets and articles and reconstruct the frames bolstering the attempted pushback. None of the frames we found were new. Rather, they reflect yet another moment of public consternation and its limitations in coming to terms with the versatile repertoire of populist truth-tampering.

Analisis Alih Kode dan Campur Kode dalam Media Sosial Twitter Akun @KuntoAjiW

The mastery of more and more languages ​​causes a change in the use of one language with another in the communication process. The use of languages ​​with different ethnic backgrounds will also provide different language variations in the communication process. One of the language variations is in the form of code switching and code mixing. Code switching and code mixing are the changing of a particular language or variety of language into another language. Code switching and code mixing can occur in bilingual or multilingual communities. Language mixing occurs in the context of formal and non-formal speech. Code switching and code mixing can not only occur in direct speech, but can also occur in social media, especially Twitter. This study aims to identify forms and describe the factors that influence the occurrence of code switching and code mixing on the Twitter account @KuntoAjiW. The method used in this research is descriptive qualitative method. Data was obtained through observation and documentation on social media Twitter. The results of this study are in the form of code switching and code mixing, as well as factors that influence code switching and code mixing on social media Twitter on the @KuntoAjiW account. The forms of code switching and code mixing contained in the @KuntoAjiW account are Indonesian, Javanese and English. Factors that influence the occurrence of code-switching and code-mixing on the @KuntoAjiW account are the habits of speakers, speech partners, the presence of third speakers, and the use of more popular terms and topics of conversation..

Exploring the concept of financial domination on social media: sentiment and text analysis on Twitter

ABSTRACT In today’s digital culture, we face a new behavior that started on Twitter, a social media platform with a large user base. This study explores how users participate in the financial slave-themed Twitter discussions and the master-slave relationship network. Accordingly, the sample consisting of the Twitter account messages which seek to meet financial slaves and mistresses is examined using text and sentiment analysis. Within the scope of the study, 277,293 tweets related to financial slavery were collected between May 2020 and November 2021, and text/sentiment analysis were performed on findom (financial domination) tweets. The keywords used in the analysis were selected from the most tweeted concepts related to financial domination and slavery (“financial slave,” #financialslave, #findom, #humanatm, #paypig, “financial domination”). The analysis of the discursive structures in the text/sentiment analysis results revealed that certain sentiments and emotions such as trust and joy were pre-requisite to establish online findom relationship. Female domination (femdom) related tweets were more prevalent in tweets while the edges between findom fetish and other kinks (foot fetish, bdsm, porn etc.) were somewhat blurred on Twitter. These show that there are vibrant user base and community on Twitter and the studies like ours are important to understand communicative dimension of financial domination.

COVID-19 and telemedicine: A netnography approach

The COVID-19 pandemic has consolidated some trends that already existed in our society. Perhaps one of the most visible is the transformation of society towards greater digitisation. Digitalisation has gained weight in all aspects of our lives, and from the point of view of the health system we find an example in the slow historical adoption of telemedicine, which contrasts sharply with the massive conversion to this technology as a tool for social distancing. In this sense, the homebound population is the one most affected by the pandemic and the one that could benefit the most from the use of telemedicine. Using a netnography approach and based on the stimulus-organism-response paradigm, this study proposes to analyse the evolution of perception about telemedicine using the opinions expressed on Twitter. The primary technical tasks of the study incorporate the analysis of topics and the review of emotions and positive image perception using natural language processing. Specifically, tweets about telemedicine generated by the Spanish community are analysed in this work. The findings show that the COVID-19 pandemic has affected emotions and topics of interest related to telemedicine. This has changed the image that it had and the behaviour of the Twitter community in Spain. In conclusion, the study results suggest that changes in health systems affect people's emotions and behaviours.

Point of Care Ultrasound Training in Nephrology: Twitter Poll as a Modern Tool for Development of an Effective Curriculum

Introduction: Point of care ultrasonography (POCUS) is being increasingly recognized as an adjunct to physical examination in the field of nephrology. However, paucity of trained faculty and standardized curricula remain key barriers to widespread adoption of this skill as well as development of reliable quality assessment programs at the institutional level. Herein, we sought to explore the utility of Twitter polls to gain insights into knowledge deficits of the learners for making curricular improvements while simultaneously disseminating POCUS pearls and pitfalls. Methods: A series of 57 single-question polls were tweeted over a 12-month period, each containing an ultrasound image or a video asking for correct interpretation. These were sent out from the Twitter handle of NephroPOCUS.com (@NephroP), an online POCUS education tool. The answer and a brief explanation were shared in a subsequent tweet at the end of the voting period. Information on the percentage of correct answers, Tweet impressions, and engagements was collected and analyzed by the pre-determined difficulty level (I-III) and the organ/learning objective being tested. Results: The number of responses per poll was 228 ± 94.6 (mean ± SD), and the percentage of correct responses was 57.9 ± 17.5 (mean ± SD). 16 (of 57) polls received less than 50% correct responses, of which 8 belonged to level III difficulty. The learning objectives that received the least number of correct responses in the kidney, cardiac, lung, vascular, and other categories were identification of end-stage kidney (16.2% correct answers), right pleural effusion on the parasternal short axis view of the heart (29%), right pleural effusion from the subxiphoid window (39%), grading of systemic venous congestion (27.3%), and identification of ascites on the right lateral chest window (15%), respectively. The overall engagement rate was 6.96%, which was above the median for health and higher education-related tweets on Twitter. Targeted didactic material was developed based on these results, published on various open-access nephrology education platforms. Conclusions: Twitter polls aid in identifying the knowledge gaps among POCUS learners. Information obtained from the polls can be used to improve POCUS-related curricula and develop targeted educational material to facilitate remote learning.

The evolution of social media in nephrology education: A mini-review.

Social media is defined as "a group of Internet-based applications that build on the ideological and technological foundations of Web 2.0, that allow the creation and exchange of user-generated content". Social media can be used in medical education to enhance knowledge sharing among peer groups and the public in general. The internet revolutionized learning by allowing easier dissemination of knowledge that did not depend on printing and physical distribution of books, journals, or magazines. According to a report from 2018, 95% of students have access to smartphones and 45% are online at any given time. Social media platforms are powerful tools to spread knowledge by the way of stories, videos, and educational games. Both formal and informal learning can be achieved with the use of social media. The microblogging website Twitter has become a popular social media platform by many in medical education including the nephrology community. Twitter, for example, is used to build communities, discuss journal articles, inform the community of conferences, share infographics and visual abstracts of original research work. As an example, it can be difficult for women in nephrology to connect and travel to make a physical presence. The use of social media allows women to connect via webinars and Women in Nephrology (WIN) India live Twitter chats. Thus, social media can help facilitate networking and collaboration with nephrologists all over the world. Social media has limitations as well. Insensitive posts can have a detrimental effect on one's career. A survey has shown that increased use of social media can contribute to addiction, anxiety, diminished self-esteem, and even depression. Hence, in order to effectively use social media to contribute positively to one's career, we recommend considering the positive and negative aspects of social media.This review will discuss the various social media platforms and how they have been applied to nephrology education.

Korean Wave and NCT Dream Brand Ambassador and its Influence on Interest in Buying Products on Twitter Followers @lemonilo

This study aims to analyze the influence of the Korean wave and the NCT Dream brand ambassador from the South Korean boy group on buying interest in Mie Lemonilo products. Intense competition makes a brand must be selective in promoting its products in order to compete in a healthy manner. Therefore, trending marketing activities are carried out by companies in this digital era, namely taking advantage of the current Korean wave trend and the popularity of celebrities by using brand ambassadors. This study uses the A-T-R theory (Awareness-Trial & Reinforcement) with the analytical tool used is the quantitative method by distributing questionnaires. The data used in this research is primary data using a questionnaire with a sample of 100 people from followers of the official Twitter account @lemonilo, totaling 33,120 followers (7 April 2022). The results of the study partially show that the coefficient value of the Korean wave variable (X1) has a positive value of 0.606 and the NCT Dream variable as a brand ambassador (X2) has a positive value of 0.324 on interest in buying Lemonilo Noodles (Y). Simultaneously, there is an influence between the independent variables Korean Wave and Brand Ambassador on the dependent variable Purchase Interest of 47.4%, which means that there is the influence of Korean Wave and NCT Dream as Brand Ambassadors on Purchase Interest for Lemonilo Noodle products.

From Opposition Leader to Prime Minister: Giorgia Meloni and Women’s Issues in the Italian Radical Right

Under the motto “God, homeland, and family”—but also by stressing one further important marker of social identity, i.e., gender—Italian radical right party leader Giorgia Meloni multiplied her party seats in parliament from 2013 onwards. After the 2022 elections, she became the first woman prime minister in Italy. Starting from an overview of the figure of Giorgia Meloni as a radical right woman leader, we explore her and her party’s position on women-related issues and their relevance while exploring, in opposition, two different contexts: representative institutions and social media. To do that, we draw on parliamentary data—bills and parliamentary questions introduced in parliament by Fratelli d’<em>Italia</em>—and on Meloni’s public discourse—examined in an analysis of all the tweets posted by her official Twitter account, between 2013 and 2021. As expected, a low saliency of women’s issues appears in all the types of data examined, although some of them are more exposed to the shift in attention caused by the rise of related trend topics. Both Meloni and her party are strong supporters of the “natural family” and make use of women’s issues in claiming femonationalist arguments, especially on social media. However, Meloni and her party cannot be considered as fully “neo-traditional,” as are other similar parties in Europe, but rather as a combination of “neo-traditional” and “modern-traditional.”

JACEP open annual report 2022.

JACEP open annual report 2022.

B2B value co-creation influence on engagement: Twitter analysis at international trade show organizer

PurposeThis paper studies, based on the theory of service-dominant logic, the effect of value co-creation practices (linking and materializing) on engagement dimensions (popularity, commitment and virality). The main objective is to analyze the influence of value co-creation practices on engagement at international trade shows organizer association on Twitter.Design/methodology/approachThis paper studies the usage of Twitter by the Specialty Food Association, which organizes one of the top five foods and beverage international trade show in the United States. To achieve the research objective, the authors have analyzed 1,608 posts on Twitter from the Twitter account @Specialty_Food. A content analysis was performed using Krippendorff's (2004) recommendations, and the data were analyzed using regression analysis with optimal scaling and Kruskal–Wallis Test.FindingsAccording to the results, some materializing practices influence popularity, commitment, virality and global engagement on Twitter. While the usage of some linking practices influences respectively commitment and popularity.OriginalityThese results provide valuable information for business-to-business (B2B) contexts and answer a research gap reported in previous literature, which affirms that more research is needed about the relationship between service systems and engagement. From a general view, to generate more engagement on social media in B2B contexts, it is recommended to prioritize posts that incorporate live and online events based on collaborative and dynamic human interactions, following by business ideas and business cases.

What Tweets and YouTube comments have in common? Sentiment and graph analysis on data related to US elections 2020.

Most studies analyzing political traffic on Social Networks focus on a single platform, while campaigns and reactions to political events produce interactions across different social media. Ignoring such cross-platform traffic may lead to analytical errors, missing important interactions across social media that e.g. explain the cause of trending or viral discussions. This work links Twitter and YouTube social networks using cross-postings of video URLs on Twitter to discover the main tendencies and preferences of the electorate, distinguish users and communities' favouritism towards an ideology or candidate, study the sentiment towards candidates and political events, and measure political homophily. This study shows that Twitter communities correlate with YouTube comment communities: that is, Twitter users belonging to the same community in the Retweet graph tend to post YouTube video links with comments from YouTube users belonging to the same community in the YouTube Comment graph. Specifically, we identify Twitter and YouTube communities, we measure their similarity and differences and show the interactions and the correlation between the largest communities on YouTube and Twitter. To achieve that, we have gather a dataset of approximately 20M tweets and the comments of 29K YouTube videos; we present the volume, the sentiment, and the communities formed in YouTube and Twitter graphs, and publish a representative sample of the dataset, as allowed by the corresponding Twitter policy restrictions.