#WashTheHate: Understanding the Prevalence of Anti-Asian Prejudice on Twitter During the COVID-19 Pandemic

Prejudice and hate directed toward Asian individuals has increased in prevalence and salience during the COVID-19 pandemic, with notable rises in physical violence. Concurrently, as many governments enacted stay-at-home mandates, the spread of anti-Asian content increased in online spaces, including social media. In the present study, we investigated temporal and geographical patterns in social media content relevant to anti-Asian prejudice during the COVID-19 pandemic. Using the Twitter Data Collection API, we queried over 13 million tweets posted between January 30, 2020, and April 30, 2021, for both negative (e.g., #kungflu) and positive (e.g., #stopAAPIhate) hashtags and keywords related to anti-Asian prejudice. In a series of descriptive analyses, we found differences in the frequency of negative and positive keywords based on geographic location. Using burst detection, we also identified distinct increases in negative and positive content in relation to key political tweets and events. These largely exploratory analyses shed light on the role of social media in the expression and proliferation of prejudice as well as positive responses online. © 2022 IEEE.

Don't Be a Victim during a Pandemic! Analysing Security and Privacy Threats in Twitter during COVID-19

There has been a huge spike in the usage of social media platforms during the COVID-19 lockdowns. These lockdown periods have resulted in a set of new cybercrimes, thereby allowing attackers to victimise social media users with a range of threats. This paper performs a large-scale study to investigate the impact of a pandemic and the lockdown periods on the security and privacy of social media users. We analyse 10.6 Million COVID-related tweets from 533 days of data crawling and investigate users' security and privacy behaviour in three different periods (i.e., before, during, and after the lockdown). Our study shows that users unintentionally share more personal identifiable information when writing about the pandemic situation (e.g., sharing nearby coronavirus testing locations) in their tweets. The privacy risk reaches 100% if a user posts three or more sensitive tweets about the pandemic. We investigate the number of suspicious domains shared on social media during different phases of the pandemic. Our analysis reveals an increase in the number of suspicious domains during the lockdown compared to other lockdown phases. We observe that IT, Search Engines, and Businesses are the top three categories that contain suspicious domains. Our analysis reveals that adversaries' strategies to instigate malicious activities change with the country's pandemic situation. © 2013 IEEE.

Measuring the Interference Effect of Bots in Disseminating Opposing Viewpoints Related to COVID-19 on Twitter Using Epidemiological Modeling

The activity of bots can influence the opinions and behavior of people, especially within the political landscape where hot-button issues are debated. To evaluate the bot presence among the propagation trends of opposing politically-charged viewpoints on Twitter, we collected a comprehensive set of hashtags related to COVID-19. We then applied both the SIR (Susceptible, Infected, Recovered) and the SEIZ (Susceptible, Exposed, Infected, Skeptics) epidemiological models to three different dataset states including, total tweets in a dataset, tweets by bots, and tweets by humans. Our results show the ability of both models to model the diffusion of opposing viewpoints on Twitter, with the SEIZ model outperforming the SIR. Additionally, although our results show that both models can model the diffusion of information spread by bots with some difficulty, the SEIZ model outperforms. Our analysis also reveals that the magnitude of the bot-induced diffusion of this type of information varies by subject. © 2023 IEEE Computer Society. All rights reserved.

Applying an Epidemiological Model to Evaluate the Propagation of Toxicity related to COVID-19 on Twitter

The prevalence of social media has increased the propagation of toxic behavior among users. Toxicity can have detrimental effects on users' emotion and insight and disrupt beneficial discourse. Evaluating the propagation of toxic content on social networks such as Twitter can provide the opportunity to understand the characteristics of this harmful phenomena. Identifying a mathematical model that can describe the propagation of toxic content on social networks is a valuable approach to this evaluation. In this paper, we utilized the SEIZ (Susceptible, Exposed, Infected, Skeptic) epidemiological model to find a mathematical model for the propagation of toxic content related to COVID-19 topics on Twitter. We collected Twitter data based on specific hashtags related to different COVID-19 topics such as covid, mask, vaccine, and lockdown. The findings demonstrate that the SEIZ model can properly model the propagation of toxicity on a social network with relatively low error. Determining an efficient mathematical model can increase the understanding of the dynamics of the propagation of toxicity on a social network such as Twitter. This understanding can help researchers and policymakers to develop methods to limit the propagation of toxic content on social networks. © 2022 IEEE Computer Society. All rights reserved.

What Really Drives the Spread of COVID-19 Tweets: A Revisit from Perspective of Content

COVID-19 content spreads wildly on social media and produces significant effects in both causing social panic and assisting pandemic management. However, what really enhances the diffusion of pandemic-related content during COVID-19, particularly from the perspective of the content itself, remains unexplored. Using large-scale COVID-19 tweets posted on Twitter, this paper empirically examines the effects of the four key characteristics, namely emotions, topics, hashtags, and mentions, on information spread in the pandemic. The empirical results show that most negative emotions have positive effects on retweeting. Nevertheless, the positive effect of trust on retweeting is unexpectedly the strongest. And the positive effects of the political topics and mentioning politicians further indicate that people are sensitive to the politicization of information during the pandemic. The strongest anger intensity in the political topic also needs to be noticed. The results complement the extant understanding of information diffusion during COVID-19 and provide insights for the governments to understand the psychology and behavior of large population during disasters like global pandemics. © 2022 IEEE.

Identifying Targeted and Generalized Offensive Speech from Anti-asian Social Media Conversations

During the Covid-19 pandemic Asian-Americans have been targets of prejudice and negative stereotyping. There has also been volumes of counter speech condemning this jaundiced attitude. Ironically, however, the dialogue on both sides is filled with offensive and abusive language. While abusive language directed at Asians encourages violence and hate crimes against this ethnic group, the use of derogatory language to insult alternative points of view showcases utter lack of respect and exploits people's fears to stir up social tensions. It is thus important to identify and demote both types of offensive content from anti-Asian social media conversations. The goal of this paper is to present a machine learning framework that can achieve the dual objective of detecting targeted anti-Asian bigotry as well as generalized offensive content. Tweets were collected using the hashtag #chinavirus. Each tweet was annotated in two ways;either it condemned or condoned anti-Asian bias, and whether it was offensive or non-offensive. A rich set of features both from the text and accompanying numerical data were extracted. These features were used to train conventional machine learning and deep learning models. Our results show that the Random Forest classifier can detect both generalized and targeted offensive content with around 0.88 accuracy and F1-score. Our results are promising from two perspectives. First, our approach outperforms contemporary efforts on detecting online abuse against Asian-Americans. Second, our unified approach detects both offensive speech targeted specifically at Asian-Americans and also identifies its generalized form which has the potential to mobilize a large number of people in socially challenging situations. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

A Linguistic Analysis of Humor Related to COVID-19 in Jordanians Hashtags

This study explores Jordanians' hashtags related to COVID-19 that aim at creating a sense of humor on Facebook. To achieve the aim of this research, a sample was collected randomly from the Facebook posts based on four popular hashtags that had been widely used among Jordanian society since the outbreak of COVID-19 until the present day. The hashtags selected for this study are "all humanity," "dried and died," "bats' Sajiyeh" and "I will let my father interfere”. The results of the study reveal that Jordanians mostly use these hashtags to create humor rather than to convey news stories. The results also show that Jordanians commonly use two types of humor: language-based and reference-based. In the first type, they use linguistic devices that include phonological, syntactic, and semantic aspects. In contrast, in reference-based humor, some cultural and religious references were employed. © 2022 DSR Publishers/The University of Jordan.

From karaoke to lip-syncing: performance communities and TikTok use in Japan

This paper discusses the versatile use of TikTok among Japanese media users in the context of the platform's increased appeal during the COVID-19 pandemic. Japanese users have adopted global trends of sharing creative content under prominent hashtags to spread a sense of togetherness in a time of social isolation. As social forms of entertainment are disrupted and paused, the practice of singing and dancing on TikTok is substituted for the joy of singing in a karaoke bar. This study adopts a walkthrough method to provide an analysis of TikTok's sociotechnical affordances and employs a content analysis for close reading of users' videos and their accompanying captions and hashtags. The study reveals that the socialities previously afforded by karaoke cultures linger in TikTok song and idol dance challenges and duets, hashtag initiatives mimicking karaoke practices, and users' endeavours to become ‘TikTok famous'. © The Author(s) 2022.

Sentiment analysis of COVID-19 tweets from selected hashtags in Nigeria using VADER and Text Blob analyser

BackgroundInformation is essential for growth;without it, little can be accomplished. Data gathering has seen significant changes throughout the previous few centuries because of the certain transitory medium. The look and style of information transference are affected by the employment of new and emerging technologies, some of which are efficient, others are reliable, and many more are quick and effective, but a few were disappointing for various reasons. AimsThis study aims at using TextBlob and VADER analyser with historical tweets, to analyse emotional responses to the coronavirus pandemic (COVID-19). It shows us how much of a sociological, environmental, and economic impact it has in Nigeria, among other things. This study would be a tremendous step forward for students, researchers, and scholars who want to advance in fields like data science, machine learning, and deep learning.MethodologyThe hashtag ‘COVID-19' was used to collect 1,048,575 tweets from Twitter. The tweets were pre-processed with a Twitter tokenizer, while TextBlob and Valence Aware Dictionary for Sentiment Reasoning (VADER) were used for text mining and sentiment analysis, respectively. Topic modelling was done with Latent Dirichlet Allocation and visualized with Multidimensional scaling.ResultsThe result of the VADER sentiment returned 39.8%, 31.3%, and 28.9%, positive, neutral, and negative sentiment, respectively, while the result of the TextBlob sentiment returned 46.0%, 36.7%, and 17.3%, neutral, positive, and negative sentiment, respectively.ConclusionWith all of this, information from social media may be used to help organizations, governments, and nations around the world make smart and effective decisions about how to restrict and limit the negative effects of COVID-19. Also, know the opinion and challenges of people, then deal with the problem of misinformation. It is concluded that with popular belief a significant number of the populace regards COVID-19 as a virus that has come to stay, some believe it will eventually be conquered.

Enacting polyvocal scorn in #CovidConspiracy tweets: The orchestration of voices in humorous responses to COVID-19 conspiracy theories.

Despite the abundance of research into conspiracy theories, including multiple studies of Covid-19 conspiracy theories in particular, user reactions to conspiracy theories are an underexplored area of social media discourse. This study aims to fill this gap by examining a dataset of humorous responses to proliferating COVID-19 conspiracy theories based on a corpus of tweets bearing the pejorative hashtag #CovidConspiracy. We report the complex orchestration of heteroglossic discursive voices in these posts to reveal their rhetorical function, oriented towards expressing a negative stance and, in some cases, amounting to ridicule. The discursive effects of this interplay of voices entail imitation, parody, mockery and irony on the micro level, while on the interactional (macro) level, anti-conspiracy tweets jointly enact what we dub "polyvocal scorn". It expresses multiple users' trenchant critique and contempt for conspiracy theories, while the humour of the tweets serves to display the users' wit and superiority over conspiracy theorists.

Sentiment analysis of COVID-19 tweets from selected hashtags in Nigeria using VADER and Text Blob analyser

BackgroundInformation is essential for growth;without it, little can be accomplished. Data gathering has seen significant changes throughout the previous few centuries because of the certain transitory medium. The look and style of information transference are affected by the employment of new and emerging technologies, some of which are efficient, others are reliable, and many more are quick and effective, but a few were disappointing for various reasons. AimsThis study aims at using TextBlob and VADER analyser with historical tweets, to analyse emotional responses to the coronavirus pandemic (COVID-19). It shows us how much of a sociological, environmental, and economic impact it has in Nigeria, among other things. This study would be a tremendous step forward for students, researchers, and scholars who want to advance in fields like data science, machine learning, and deep learning.MethodologyThe hashtag ‘COVID-19' was used to collect 1,048,575 tweets from Twitter. The tweets were pre-processed with a Twitter tokenizer, while TextBlob and Valence Aware Dictionary for Sentiment Reasoning (VADER) were used for text mining and sentiment analysis, respectively. Topic modelling was done with Latent Dirichlet Allocation and visualized with Multidimensional scaling.ResultsThe result of the VADER sentiment returned 39.8%, 31.3%, and 28.9%, positive, neutral, and negative sentiment, respectively, while the result of the TextBlob sentiment returned 46.0%, 36.7%, and 17.3%, neutral, positive, and negative sentiment, respectively.ConclusionWith all of this, information from social media may be used to help organizations, governments, and nations around the world make smart and effective decisions about how to restrict and limit the negative effects of COVID-19. Also, know the opinion and challenges of people, then deal with the problem of misinformation. It is concluded that with popular belief a significant number of the populace regards COVID-19 as a virus that has come to stay, some believe it will eventually be conquered.

From #iononriapro to #ioapro: analysing hashtag activism in the Italian restaurant Twittersphere during the 2020 lockdown

Purpose: In this article, the authors analyse the impact of the 2020 lockdown and the subsequent measures to contain the spread of COVID-19 in Italy in the hospitality industry by looking at the social demands brought forward by the restaurant sector. Design/methodology/approach: To analyse social demands, the authors choose Twitter as an observation point using two hashtags as keywords to scratch the data: #iononriapro and #ioapro, which correspond to two different instances conveyed by the same subject: the restaurant sector. The instances linked to the hashtags produced different levels of engagement and penetration within the social structure and digital platform. To analyse the first block of data linked to the first hashtag-flag #iononriapro, the authors used content analysis. To analyse the second and third block of data linked to the hashtag-flag #ioapro, the authors used an automatic procedure, emotional text mining. Findings: The analysis procedures allow us to reconstruct the positioning of the topics of closures and reopenings due to lockdown in this sector and to identify two explanatory dimensions: structural and affective, which explain the tension that has emerged between the State and the restaurant sector around COVID-related closures. Originality/value: The study's findings not only contribute to the current understandings of the birth, transformation and penetration of social issues by the restaurant sector over the specific period linked to the COVID-19 pandemic and the measures imposed for its containment but are also valuable to analyse the dynamics through which Twitter hashtags and the social issues they represent find strength or lose interest in the public. © 2022, Emerald Publishing Limited.

Social Media Consistency Analysis Ministry of State-Owned Enterprises in Indonesia During the COVID-19 Pandemic

This study aims to identify shifts in the production of social media information content in the industrial world during the COVID-19 pandemic in Indonesia. Official government social media accounts during the COVID-19 pandemic era experienced significant changes in disseminating information. The research was conducted on the official account @KemenBUMN. Indonesia is a national government agency in charge of fostering and managing state-owned enterprises. This research method uses the Q-DAS approach (Qualitative Data Analysis Software) and NVivo 12. The data source for this research is the official account activity of @KemenBUMN, using NCapture from the Twitter social media activity of the Indonesian Ministry of State-Owned Enterprises. The results found in this study for the production of information content about industrial developments during the COVID-19 pandemic are quite consistent from 2021 to 2022. The amount of content produced during the COVID-19 pandemic was more than 20 tweets in one month for a year starting from March 2021 to March 2022. In the results of Wordcloud analysis, the most widely used keywords are "BUMN” and "Sobat BUMN." The dominant information submitted by the @KemenBUMN account is information about activities and developments from various fields managed by the Ministry of SOEs for one year. The ministry of state-owned enterprises is quite active in greeting their followers with the hashtags # SobatBUMN and #bumnuntukindonesia in each of their tweets strategy for disseminating information during the pandemic by mentioning MNC official accounts in Indonesia. This is evidenced by the widespread use of content with the hashtags #bumnuntukindonesia and #sobatBUMN aimed at partners. That the production of SOE information social media content does not focus on dealing with COVID-19. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

Detection of Social Media Hashtag Hijacking Using Dictionary-based and Machine Learning Methods

Nowadays, hashtags are widely utilized on all social media platforms since they deliver numerous benefits, particularly for corporations aiming to reach a larger audience. However, hashtag exploitation has resulted in the problem of hashtag hijacking, which is a type of cyber content threat that anyone or any organization can carry out. As a result, this research presents a framework for detecting social media hashtag hijacking through machine learning algorithms. This paper aims to identify methods to classify relevant and irrelevant hashtags to their contents. This paper demonstrates the unsupervised machine learning method, namely the dictionary-based approach, to classify the relevance of hashtags with the content of tweets on an unlabeled dataset, and also the implementation of supervised machine learning methods, including the Support Vector Machine (SVM), Naive Bayes classifier, and Decision Tree algorithms, to classify the relevance of hashtags used with their contents and compare the machine's performances on labeled datasets. Our results showed that the Support Vector Machine (SVM) performs the best in classifying the relevance of hashtags with an accuracy of 93.36%, an F1 score of 96.19% and ROC-AVC score of 97.22 %. The findings of the study present an automated detection framework for hashtag hijacking that can overcome the limitations of previous studies and adapt to external threats with high performance over time. © 2022 IEEE.

A Systematic Approach for Contextualizing Focal Structure Analysis in Social Networks

Focal Structures are key sets of individuals who may be responsible for coordinating events, protests, or leading citizen engagement efforts on social media networks. Discovering focal structures that can promote online social campaigns is important but complex. Unlike influential individuals, focal structures can effect large-scale complex social processes. In our prior work, we applied a greedy algorithm and bi-level decomposition optimization solution to identify focal structures in social media networks. However, the outcomes lacked a contextual representation of the focal structures that affected interpretability. In this research, we present a novel Contextual Focal Structure Analysis (CFSA) model to enhance the discovery and the interpretability of the focal structures to provide the context in terms of the content shared by individuals in the focal structures through their communication network. The CFSA model utilizes multiplex networks, where the first layer is the users-users network based on mentions, replies, friends, and followers, and the second layer is the hashtag co-occurrence network. The two layers have interconnections based on the user hashtag relations. The model's performance was evaluated on real-world datasets from Twitter related to domestic extremist groups spreading information about COVID-19 and the Black Lives Matter (BLM) social movement during the 2020–2021 time. The model identified Contextual Focal Structure (CFS) sets revealing the context regarding individuals’ interests. We then evaluated the model's efficacy by measuring the influence of the CFS sets in the network using various network structural measures such as the modularity method, network stability, and average clustering coefficient values. The ranking Correlation Coefficient (RCC) was used to conduct a comparative evaluation with real-world scenarios. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

Femitags for feminist connected crowds in Latin America and Spain.

In recent years, women are acting all over the world against gender violence and femicide. This new wave of feminist claims is characterized by the intensive use of social media to spread consciousness and amplify influence. For this research, we analyse three femitags (i.e., feminist hashtags) from Twitter that have been relevant in different crucial mobilizations in Argentina, Spain, and Mexico. These are three hashtags with different functions for activism that have shown special relevance due to their continuity or their intensity in the Spanish-speaking area between 2015 and 2020 (before the confinement due to the COVID-19 pandemic). #NiUnaMenos (#NotASingleWomanLess) started in Argentina in 2015 and called to massive mobilizations on the streets. #Cuéntalo (#TellIt) was initiated in Spain in 2018 for sexual abuse disclosure. #NiUnaMas (#NotASingleWomanMore) trended in México around 2020 to denounce every new victim of rape or femicide. We analyse how those hashtags have spread in the Spanish-speaking region, what kind of social actors have been involved and what has been the role of opinion leaders. All data were collected with academic access to the Twitter API during December 2021. We have found that the most influential actors in the conversation are contingent and circumstantial, the leadership structure tends towards horizontality, and opinion leaders with large numbers of followers are only important in very specific moments. In all cases, femitags serve as a toolbox for action and build up an archive of grievances with a transnational dimension. Furthermore, all of them point out that structural violence against women leads to feminicide.1.

Who’s the Bigger Brand After COVID-19 Pandemic? An Assessment of Fan Engagement During Euro 2020

Post COVID-19 pandemic, sports events and sports activities have been severely affected. The mega sports events were either postponed or held in the absence of live audience. Through this study we investigate the progressive use of social media by fans and other stakeholders to express their support to favorite sports teams, athletes, coaches, sports organizations, sponsors and more during COVID-19. UEFA Euro 2020 was conducted across 12 countries with an intent to show unity and bring normalcy in sports business during the third wave of COVID-19. Hashtag analysis and mention analysis have been performed to find sports teams, athletes or other stakeholders that were directly being discussed about by the fans. We also focused on tweet context annotations that provide entities as pairs of domain and entity collected from tweets’ text. Our results indicated that hashtags and mentions alone cannot substantially justify the popularity of any entity. Thus, from the point of view of identifying any athlete, team, organization or any sponsor as a brand, tweet context annotations can be valuable from the perspective of E-Branding, E-Marketing and E-Commerce. © 2022, IFIP International Federation for Information Processing.

COVID-19 vaccine sentiment analysis using public opinions on Twitter.

Twitter, as is well known, is one of the most active social media platforms, with millions of tweets posted every day, in which different people express their opinions on topics such as travel, economic concerns, political decisions, and so on. As a result, it is a useful source of knowledge. We offer Sentiment Analysis using Twitter Data for the research. Initially, our technology retrieves currently accessible tweets and hashtags about various types of covid vaccinations posted on Twitter through using Twitter's API. Following that, the imported Tweets are automatically configured to generate a collection of untrained rules and random variables. To create our model, we're utilizing, Tweepy, which is a wrapper for Twitter's API. Following that, as part of the sentiment analysis of new Messages, the software produces donut graphs.

The Success of Socialization Vaccination Program Policies in DKI Jakarta Through Social Media

This paper aims to see the success of the socialization of the COVID-19 vaccine program policy from the DKI Jakarta Provincial Government. This study analyzed data from #vaksindulu created by the Twitter account of the Jakarta Special Capital Region (DKI) Provincial Government (@PemprovDKIJakarta) which is a form of socialization of the COVID-19 vaccine through social media. This research used descriptive qualitative research. Data analysis was implemented using NVivo 12 Plus software, data retrieval from #Vaksindulu created by the DKI Jakarta Provincial Government Twitter account via NCapture from NVivo 12 Plus with Web Chrome. The data was the content of vaccine socialization taken from the Twitter account @PemprovDKIJakarta with the hashtag #vaksindulu. The results found that the highest use of #vaksindulu was from June to August. The DKI Jakarta Provincial Government’s strategy most often used socialization mechanisms, socialization materials, collaboration socialization, and participation. The DKI Jakarta Provincial Government, in its socialization orientation, communicates more often with government sectors than the private sector and NGOs. This research will be a benchmark for the success of the DKI Jakarta Provincial Government’s socialization through social media and can be a reference for further research. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

Socialization Strategy in the Disability Vaccination Program Through Social Media in Indonesian

This study aims to determine the role of the Indonesian government in disseminating the disability vaccination program through social media, especially on Twitter. This research data is seen and analyzed in the social media accounts of @KemenkesRI, @KemensosRI, and @Kemkominfo. The method in this study uses Q-DAS (Qualitative Data Analysis Software) Nvivo 12 plus. The data obtained are tweets from the Twitter accounts of the Ministry of Social Affairs, Ministry of Health, and Ministry of Information Technology. This study found that the Ministry of Health was very intensive in disseminating information and distributing vaccination programs compared to the social media accounts of the Ministry of Social Affairs and the Ministry of Communication and Information. Dissemination of vaccination information for persons with disabilities on social media Twitter @ Ministry of Social Affairs in Vaccination Distribution information. Meanwhile, in conveying information, the Twitter social media account @Kemkominfo is more dominant in using symbols or hashtags. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.