Twitter Research Articles

How does Twitter account moderation work? Dynamics of account creation and suspension on Twitter during major geopolitical events

Social media moderation policies are often at the center of public debate, and their implementation and enactment are sometimes surrounded by a veil of mystery. Unsurprisingly, due to limited platform transparency and data access, relatively little research has been devoted to characterizing moderation dynamics, especially in the context of controversial events and the platform activity associated with them. Here, we study the dynamics of account creation and suspension on Twitter during two global political events: Russia’s invasion of Ukraine and the 2022 French Presidential election. Leveraging a large-scale dataset of 270M tweets shared by 16M users in multiple languages over several months, we identify peaks of suspicious account creation and suspension, and we characterize behaviors that more frequently lead to account suspension. We show how large numbers of accounts get suspended within days of their creation. Suspended accounts tend to mostly interact with legitimate users, as opposed to other suspicious accounts, making unwarranted and excessive use of reply and mention features, and sharing large amounts of spam and harmful content. While we are only able to speculate about the specific causes leading to a given account suspension, our findings contribute to shedding light on patterns of platform abuse and subsequent moderation during major events.

Does Public Sentiment Impact Stock Price Movements? Evidence from India

This study analyses the impact of a weighted measure of public sentiment about firms on their stock price movement using a sample of 5.4 million tweets from the official Twitter handles of the 437 largest Indian firms. This article contributes to the literature by finding that general public discussion about firms and the resulting sentiment impact firms’ stock price movement in India. Moreover, the impact is greater during trading hours than off-market hours due to immediate action by traders in the former. It is also found that negative public sentiment has a more significant impact than positive sentiment on returns and volatility. JEL Codes: G14, G40, G41

When Twitter blocked Trump: The paradox, ambivalence and dialectic of digitalized publics

In our text, we follow the traces of a (1) paradox, (2) an ambivalence and (3) a dialectic that constitute digitalized public spheres and discuss the resulting tensions in discourse-ethical and political-theoretical perspectives using the blocking of Donald J. Trump’s Twitter account as an example. Starting from this, we determine the conditions of constitution of the digital public sphere and locate the dynamics of its development in the dialectical tension between private and public: The fact that the two other relations of autonomy and heteronomy, intensification and polarization come to such a head is based on an insufficient socialization of all those means of production that produce the current digital public sphere. Using the example of Donald J. Trump’s recently suspended Twitter account and with a view to Habermas’s discourse ethics, we illustrate the extent to which Trump’s partly racist and conspiracy-theoretical post violates discourse ethics standards and is also highly problematic with regard to the political; however, banishment from a part of the digital public sphere is certainly not an act that should be incumbent on a private company. From this, we conclude that the normative potentials of digital public spheres can only be vol.

Alcohol policy framing in South Africa during the early stages of COVID-19: using extraordinary times to make an argument for a new normal

IntroductionPublic health and alcohol industry actors compete to frame alcohol policy problems and solutions. Little is known about how sudden shifts in the political context provide moments for policy actors to re-frame alcohol-related issues. South Africa’s temporary bans on alcohol sales during the COVID-19 pandemic offered an opportunity to study this phenomenon.MethodsWe identified Professor Charles Parry from the South African Medical Research Council as a key policy actor. Parry uses a Twitter account primarily to comment on alcohol-related issues in South Africa. We harvested his tweets posted from March 18 to August 31, 2020, coinciding with the first two alcohol sales bans. We conducted a thematic analysis of the tweets to understand how Parry framed alcohol policy evidence and issues during these ‘extraordinary times.’ResultsParry underlined the extent of alcohol-related harm during ‘normal times’ with scientific evidence and contested industry actors’ efforts to re-frame relevant evidence in a coherent and well-constructed argument. Parry used the temporary sales restrictions to highlight the magnitude of the health and social harms resulting from alcohol consumption, particularly trauma, rather than the COVID-19 transmission risks. Parry portrayed the sales ban as a policy learning opportunity (or ‘experiment’) for South Africa and beyond.ConclusionsCrisis conditions can provide new openings for public health (and industry) actors to make salient particular features of alcohol and alcohol policy evidence.

Unlocking the power of Twitter communities for startups

Social media platforms offer cost-effective digital marketing opportunities to monitor the market, create user communities, and spread positive opinions. They allow companies with fewer budgets, like startups, to achieve their goals and grow. In fact, studies found that startups with active engagement on those platforms have a higher chance of succeeding and receiving funding from venture capitalists. Our study explores how startups utilize social media platforms to foster social communities. We also aim to characterize the individuals within these communities. The findings from this study underscore the importance of social media for startups. We used network analysis and visualization techniques to investigate the communities of Portuguese IT startups through their Twitter data. For that, a social digraph has been created, and its visualization shows that each startup created a community with a degree of intersecting followers and following users. We characterized those users using user node-level measures. The results indicate that users who are followed by or follow Portuguese IT startups are of these types: “Person”, “Company,” “Blog,” “Venture Capital/Investor,” “IT Event,” “Incubators/Accelerators,” “Startup,” and “University.” Furthermore, startups follow users who post high volumes of tweets and have high popularity levels, while those who follow them have low activity and are unpopular. The attained results reveal the power of Twitter communities and offer essential insights for startups to consider when building their social media strategies. Lastly, this study proposes a methodological process for social media community analysis on platforms like Twitter.

CODE MIXING ON KRISTO IMMANUEL’S TWITTER ACCOUNT

This research is sociolinguistics research which identified code-mixing on Kristo’s Twitter account. The aim of this research is to know the type of code-mixing on Kristo’s Twitter account. This research used Wardaugh’s theory. The researcher used observational method with non-participant techniques in collecting the data by Sudaryanto. This research applied sociolinguistics identity method and sociolinguistics- competence in equalizing to analyze the data. When people want to interact with each other, they have to choose a particular code to express their feeling. Related to this, the research is written based on code-mixing as a means of language variation in sociolinguistic, and it is used in social media. The researcher found all the type of code mixing on Kristo’s twitter account. Each of the data divided into type of code mixing there are intra-sentential code mixing, intra-lexical code mixing, and involving of pronunciation code-mixing. Code mixing could happen everywhere with any condition and situation. In other words, in this situation many people are using social media and making posts that mix their language.
 Keywords : code mixing, sociolinguistic, twitter

What's trending? Reach and content of the Society for Maternal-Fetal Medicine on social media

The Society for Maternal-Fetal Medicine (SMFM) uses social media to increase awareness of the Society and its key programs and to foster community and discussion around perinatal health, especially on Twitter. The influence and role of the SMFM Twitter account in public discourse around issues relevant to pregnancy have not been studied. We sought to evaluate trends in engagement with SMFM on Twitter by analyzing SMFM follower growth and discussion topics on Twitter compared with Facebook and by quantifying public engagement during the SMFM Annual Pregnancy Meeting. This retrospective study analyzed follower growth data from August 2019 to July 2022 for SMFM Twitter (@MySMFM) and SMFM Facebook (@SocietyforMaternalFetalMedicine). We identified the top 10 Tweets and Facebook posts during the study period using Twitter analytics and Facebook data. Popularity of Tweets and Facebook posts was determined by "impressions" and "reach", respectively; these metrics reflect the number of times a post was viewed. To evaluate annual trends in SMFM Twitter engagement, we analyzed data associated with the SMFM Annual Pregnancy Meeting, including the number of Tweets using the hashtag (#SMFM(Year)) and overall impressions for the SMFM Twitter account for each meeting from 2016-20223. The absolute number of new followers for SMFM Twitter and Facebook was similar, but the relative increase and rate of follower growth was higher for Twitter than for Facebook. The Twitter account consistently gained followers while the Facebook account experienced intermittent periods of stagnancy or follower loss. More than half of the top ranked posts on Twitter and Facebook mentioned the COVID vaccine; other popular topics included COVID-19 and abortion. During the SMFM Annual Pregnancy Meeting, Tweets using the meeting hashtag consistently peaked on meeting day 4, coincident with the opening plenary session (mean number of Tweets = 1270 +/- 499). An upward trend in Annual Pregnancy meeting tweets was observed each year until 2021 - the first virtual SMFM meeting. Trends in SMFM Twitter engagement suggest increasing use and popularity of the platform for timely dissemination of pregnancy-related news, guidelines, and research. The reduction in Annual Pregnancy Meeting Tweets and impressions in 2021 and 2022 suggests the potential negative impact of virtual meetings on SMFM member engagement around Annual Meeting content.

Education Research: The Development and Utilization of a Virtual Twitter Onboarding Curriculum for Neurologists, Trainees, and Students: A Prospective Study.

Social media has increased in popularity among neurologists in the past few years without a parallel increase in training opportunities to learn how to use social media effectively. This study tests the feasibility of an asynchronous, virtual onboarding curriculum using Twitter as a tool for professional development for neurologists and neurology trainees. Neurologists and neurology trainees were recruited virtually through email, Twitter, and a listserv of the American Academy of Neurology (Synapse). Participants were excluded if they had a professional Twitter account or lived outside the United States. Participants performed all study procedures virtually, including a baseline survey followed by three 30-minute modules: introduction to NeuroTwitter, peer learning, and academic scholarship on Twitter. A postmodule survey was completed to provide postprogram curriculum feedback. Newly created Twitter accounts were followed for 3 months to track Twitter engagement. Sixty-one participants were screened, and 50 were eligible to enroll. Forty-five (90%) participants completed a consent form and baseline survey. Twenty-seven participants completed all 3 modules, and 26 (52%) completed the postmodule survey. Participants indicated that there was a role for social media in neurology but had minimal to no training on how to use it effectively. Twitter knowledge postmodule completion increased by a median of 2 of 15 questions, with a range of -1 to +5. There were no technical barriers with a virtual-based curriculum, and participants were able to access the modules and surveys successfully. Ninety-six percent of participants would recommend the modules to colleagues. Thirty new Twitter accounts were created with an average of 33 followers, 59 following, 16 tweets, and 61 likes at 4 months. This study highlights the feasibility of virtual asynchronous content leading to an increase in Twitter knowledge among neurologists who completed our modules, though limited by a high dropout rate. Recruitment for virtual asynchronous modules was an effective approach to deliver informative and interactive content for neurologists. Further studies are needed to determine optimal content and length to promote long-term engagement with Twitter.

Curriculum Innovations: A Social Media-Based Educational Curriculum Improves Knowledge for Trainees in Neurocritical Care: Results of a Stratified Randomized Study.

The Neurocritical Care (NCC) Society Resident and Fellow Task Force's NEURON study concluded that learners had significant concerns regarding the need for educational improvement in NCC. To address these shortcomings, we identified the lack of an educational curriculum for trainees in NCC and developed a Twitter-based educational curriculum for trainees to improve knowledge in NCC. The objectives of this study were to describe the pathophysiology, delineate a systematic diagnostic approach, and apply evidence-based strategies in the management of diseases in NCC. Ten trainees developed a Tweetorial (educational content available on Twitter)-based curriculum, with individual review by at least 2 NCC faculty. Learners were recruited through Twitter and randomized to 1 of 2 groups in a wait-list control prospective study. Group 1 completed the curriculum in the first 6 months of the 2021-2022 academic year, and group 2 completed the curriculum in the second half. Tweetorials were posted weekly on a private Twitter account only available to the active learner group. Learners were assessed by a multiple-choice format test (written by the trainees and reviewed by faculty) at 3 time points: before the first Tweetorial was released (preeducational curriculum assessment), after group 1 completed all tutorials and before group 2 started the curriculum (assessment 1), and after both groups finished (assessment 2). The primary outcome was the mean score on the second and third assessments. One hundred forty-six learners were assigned to group 1 or 2 using stratified block randomization including 99 (68%) Neurology residents, 81 (55%) US-based. Each group was composed of 73 participants. A total of 20 Tweetorials were published on a private Twitter account (@NeurocriticalE). Completed assessments were obtained from 100, 32, and 18 learners for the pre-educational curriculum assessment, assessment 1, and assessment 2, respectively. Group 1 and group 2 performed similarly in the pre-educational curriculum assessment. A potential for knowledge improvement was observed in group 1 at assessments 1 and 2 when compared with the learner group 2. Group 1 had more impressions, engagements, likes, URL clicks, and media views. Although there was some learner attrition, our study demonstrates that social media can effectively deliver educational content and engage a diverse group of trainees around the globe.

Stakeholders' “voice” through social media: the case of corporate social responsibility in sport

PurposePrevious corporate social responsibility (CSR) research has mainly revolved around the “usual target” (that is, fans and consumers) that invest money, time and energy in supporting their teams in isolation while largely ignoring individual members of the public. Building on social exchange theory and social media analytics, the authors examine the social outcomes of CSR aggregated from individual members of society's perceived benefits (intangible and psychological).Design/methodology/approachRaw data were drawn from the CSR-focused Twitter accounts of six professional leagues (i.e. @nbacares, @nflplay60, @InspireChange, @thewnbpa, @Pr_nhl, @Mlsworks and @Mlbsocial). The authors collected historical data from each CSR-focused Twitter account (N = 136,076) from March 2010 to September 2022.FindingsAfter conducting sentiment analysis of public perceptions, the majority of tweets (53%) were neutral, 39% were positive and 8% were negative. All CSR-related accounts received more positive tweets about their initiatives than negative ones did. The most prevalent positive topics are supporting the community, education, youth wellness and health and inspiring the young generation. The most prevalent negative topics were related to fake, hypocrite, hate and social justice.Originality/valueThe study contributes to the CSR-sport literature by incorporating members of the general public into the stakeholder ecosystem and empirically examining their perceptions of sport organizations' CSR activities. Also, by drawing on the social exchange theory and the unique nature of social media, the authors highlight when and how the public expresses positive, neutral and negative perceptions over time. Finally, it joins a small but growing body of research that adopts the application of big data to sport management, and it measures the sentiment, frequency, distribution and topics of tweets, thereby determining positive and negative public perceptions.

The tinder swindler: Analyzing public sentiments of romance fraud using machine learning and artificial intelligence

The Tinder Swindler is a Netflix documentary that documents the stories of three women who were swindled of their life savings by a man, Simon Leviev ("Leviev"), who presented himself as the son of a wealthy diamond oligarch. The paper's main objective is to understand the sentiments shared by the public on the microblogging website Twitter on Leviev's actions towards victims. This paper is anchored with Ervin Goffman's (1959) impression management (IM) theory to provide context and theoretical insights into the analysis. IM theory offers a cultural framework to address and understand how people mold their behaviour in social contexts to alter their audience's perceptions of themselves. Data for this project came from Twitter with the hashtag #tinderswindler. In total, 47,876 tweets were collected between February 1st and March 18th. The findings reveal that most people who commented on Twitter had high neutral and positive but low negative sentiments about Leviev's actions in the Tinder Swindler. The neutral findings indicate that a significant proportion of individuals did not support Leviev's action, nor do they support the women who were defrauded. The positive sentiments reveal that Leviev's favourable self-presentation successfully persuaded people that his front-stage performance was real and that the performance resonated with Twitter users. The higher subjectivity for the negative sentiments means that the texts contain more factual information than personal opinion.

Kredibilitas Informasi di Era Post-Truth Dikalahkan Kecepatan Informasi: Pengabaian Undang Undang Informasi dan Transaksi Elektronik

Many people choose social media as a source of information that is considered the fastest and most up-to-date without knowing its credibility for sure. In the post-truth era, social media has shifted the power of logic and facts, and often the information on it is considered true. This study aims to gain an understanding of the credibility of information uploaded by the Twitter account @AREAJULID. By using a virtual ethnography approach. This qualitative research explores the existence of a phenomenon of attraction between the influence of information speed and information credibility. The results of the search on the @AREAJULID account show that many followers of the account have the assumption that the speed of content uploaded by @AREAJULID makes it a trusted source of information. They even disseminate the information by retweeting and sharing the link on other social media channels such as Facebook, TikTok and WhatsApp. The followers' actions ignore the existence of the Electronic Information and Transaction Law. The post-truth era makes the @AREAJULID account a credible source of information precisely because of the speed of uploading and not because of the truth of the information. Keywords: post-truth, virtual ethnography, information credibility

Crisis communication for public organizations: Examining Pakistan Railways' use of information technology and social media for image repair

AbstractThis study examines the induction of information technology and the use of image‐repair focused crisis response strategies on social media by Pakistan Railways amid a recent crisis. A mix‐method based content analysis (i.e., qualitative and quantitative) to investigate whether and if so, how Pakistan Railways used Benoit's suggested image restoration strategies on social media to repair its image among customers and in print media. Our results show that Pakistan Railways predominantly used reducing the offensiveness of event (40%), followed by corrective action (34.6%), evasion of responsibility (10.6%), denial (8%) and mortification (6.4%) strategies, respectively. In addition, the use of image‐repair focused crisis response strategies significantly varied by social media platform. An analysis of the publics' emotions found in their online comments reveals that, during the course of the organizational crisis communication, negative public emotions gradually subsided into ambivalent ones; and contrary to a highly negative newspaper coverage tone in the beginning of the crisis, the introduction of the Twitter handle has associated with more positive media coverage afterward. Theoretical and practical implications, especially the need for advancing social‐mediated crisis response effectiveness in developing countries, are discussed.

Using health belief model and social media analytics to develop insights from hospital-generated twitter messaging and community responses on the COVID-19 pandemic

PurposeThis study aims to examine how different hospitals utilize social media to communicate risk information about COVID-19 with the communities they serve, and how hospitals' social media messaging (firm-generated content and their local community's responses (user-generated content) evolved with the COVID-19 outbreak progression.Design/methodology/approachThis research proposes a healthcare-specific social media analytics framework and studied 68,136 tweets posted from November 2019 to November 2020 from a geographically diverse set of ten leading hospitals' social media messaging on COVID-19 and the public responses by using social media analytics techniques and the health belief model (HBM).FindingsThe study found correlations between some of the HBM variables and COVID-19 outbreak progression. The findings provide actionable insight for hospitals regarding risk communication, decision making, pandemic awareness and education campaigns and social media messaging strategy during a pandemic and help the public to be more prepared for information seeking in the case of future pandemics.Practical implicationsFor hospitals, the results provide valuable insights for risk communication practitioners and inform the way hospitals or health agencies manage crisis communication during the pandemic For patients and local community members, they are recommended to check out local hospital's social media sites for updates and advice.Originality/valueThe study demonstrates the role of social media analytics and health behavior models, such as the HBM, in identifying important and useful data and knowledge for public health risk communication, emergency responses and planning during a pandemic.

Hamas in Cyberspace: Social Media and Forms of Political Expression

This study examines the digital practices and online discourses of Hamas on Twitter, with a specific focus on the Palinfoen account linked to the Palestinian Information Centre (PIC). The study examines 3,500 tweets related to events in Palestine, which were either tweeted or retweeted by the Palinfoen account. To explore these practices, the researcher employs digital ethnography and a discourse-historical approach to analyze the collected tweets and retweets. The findings of the analysis show that the tweets revolve around key figures such as journalist Shireen Abu Akleh and Israel. Abu Akleh is portrayed as a courageous and esteemed senior journalist who became a victim of Israeli brutality. Israel, on the other hand, is depicted as a criminal entity, held responsible for the cold-blooded killing of Abu Akleh and the desecration of her coffin. The killing is presented as an inhumane and irrational act committed by Israel against a respected journalist. Additionally, the tweets from Palinfoen focus on the events at Al-Aqsa Mosque in Jerusalem. Israeli figures are described using terms like "genocidal Jews," "Israeli occupation forces," "enemy occupier gangs," and an "illegitimate regime," while Palestinian figures are referred to as "worshippers," "families," and "Muslims." The discourses promoted by Hamas on Twitter place agency and accountability on the Israeli side. In conclusion, this analysis unsurprisingly highlights how the Palinfoen Twitter account portrays Palestinian resistance as a legitimate reaction.

Developing a Web-Based Asynchronous Case Discussion Format on Social Media to Teach Clinical Reasoning: Mixed Methods Study.

Case-based learning conferences are valuable to trainees, but growing clinical demands hinder consistent attendance. Social media increasingly acts as a venue for trainees to supplement their education asynchronously. We designed and implemented a web-based asynchronous clinical case discussion series on the Twitter social media platform to fill this educational gap. The aim of this mixed methods study is to examine the nature of interactions among web-based case discussion participants and assess local attitudes regarding the educational intervention. Starting in February 2018, we posted clinical vignettes to a dedicated Twitter account with the prompt "What else do you want to know?" to stimulate discussion. The authors replied in real time when case discussion participants requested additional details. Additional data about the case were posted at regular intervals to the discussion thread to advance the overall case discussion. Participants were asked to explain their reasoning and support their conclusions when appropriate. Web-based engagement was assessed using Twitter Analytics. Participants' posts were qualitatively analyzed for themes, with special attention to examples of using clinical reasoning skills. A codebook of types of participant posts and interactions was refined iteratively. Local engagement and attitudes at our institution were assessed by surveying internal medicine trainees (n=182) and faculty (n=165) after 6 months. Over a 6-month period, 11 live case discussions were engaged with by users 1773 times. A total of 86 Twitter profiles spanning 22 US states and 6 countries contributed to discussions among participants and the authors. Participants from all training levels were present, ranging from students to faculty. Interactions among participants and the case moderators were most commonly driven by clinical reasoning, including hypothesis-driven information gathering, discussing the differential diagnosis, and data interpretation or organization. Of 71 respondents to the local survey, 29 (41%) reported having a Twitter account. Of the 29 respondents with Twitter accounts, 17 (59%) reported participating in the case discussions. Respondents agreed that case participation increased both their clinical reasoning skills (15/17, 88%) and clinical knowledge (13/17, 76%). A social media-based serialized case discussion was a feasible asynchronous teaching method for engaging web-based learners of all levels in a clinical reasoning discussion. Further study should examine what factors drive trainee participation in web-based case discussions and under what circumstances asynchronous discussion might be preferred over in-person teaching activities.

Use of Twitter as a Tool for Political Parties’ Election Campaigns

Twitter is an excellent social medium for following election events and participating in public debate. Twitter allows individuals to express themselves on crucial national problems in various ways. All political parties used Twitter to interact with voters during the general election campaign in 2019. In such a case, it is critical to understand the impact of the election campaign on Twitter on shaping young people's votes. Qualitative content analysis has been conducted to evaluate the quality of national political parties' tweets during the 2019 general election. For this, tweets from the official Twitter handles of the BJP and the INC during the 2019 general elections were selected using a checklist. A serious attempt was made to understand all units of analysis in the tweets. The present study contributes to understanding the quality of the NPPs' messages. This study also evaluated Twitter's influence on the upcoming Lok Sabha elections.

Trends in Twitter Utilization Among Academic Otolaryngologists.

To characterize Twitter utilization among academic otolaryngologists and evaluate the relationship between Twitter utilization and research productivity. Data were collected manually from accredited US otolaryngology residency programs from July-November 2021. Program and faculty demographics were documented, including citations and H-index for faculty and Doximity reputation and US News and World Report ranking for programs. Twitter metrics were also recorded. Descriptive analyses and multivariable logistic regression models were used to identify predictors of Twitter utilization. Currently, 333 (16%) faculty and 70 (62%) programs have a Twitter account. Of these, 36 (11%) and 27 (39%), respectively, were created in 2020. The regression model indicates that for each 5 unit increase in H-index, the odds of having a Twitter account increase 22% (OR 1.22, 95% CI 1.10-1.34, p = 0.0009). The number of faculty with a Twitter account predicts the existence of program Twitter accounts (OR:1.49, 95% CI 1.01-2.19, p = 0.04). Finally, of the 323 faculty with a Twitter account and available Scopus profile, we found that the number of individuals with Twitter use out of proportion to their academic productivity was low (n = 8/323). The H-index is a significant predictor of faculty Twitter accounts, whereas the number of faculty with Twitter is a significant predictor of program Twitter utilization. Although Twitter utilization is increasing, especially during the coronavirus pandemic, the findings indicate that there is ample room for growth, particularly amongst faculty with strong academic portfolios. NA Laryngoscope, 134:1190-1196, 2024.

Informational value of visual nudges during crises: Improving public health outcomes through social media engagement amid COVID‐19

In this study, we conceptualize and empirically evaluate how large‐scale organizations can utilize the informational value of visual nudges on social media to promote safety among users and thus improve public health outcomes in the context of the coronovirus desease caused by the SARS‐CoV‐2 virus (COVID‐19) pandemic. We construct a unique panel dataset combining data collected from multiple public and proprietary sources. To operationalize visual nudges from user‐generated content, we engage in extensive manual classification of images collected from Instagram (IG), Twitter (TW), and Facebook (FB). To examine the relationship between visual nudging and COVID‐19 positivity, we rely on a combination of econometric and epidemiological models. We find that when institutional actors share more images containing mask‐related information on IG, their COVID‐19 positivity rates decrease by up to 25%, on average. Also, given the fragmentary evidence behind FB and TW effects, our results provide suggestive evidence of the “boundary condition” of the visual nudge effect. Finally, empirical evidence indicates the dynamic and curvilinear effect of visual nudges on positivity over time, such that the informational value of visual nudging is most prominent if communicated 3 to 5 weeks ahead of time, on average. Our results demonstrate the informational value of visual nudges communicated through pertinent social media channels, as well as their capacity to improve public health outcomes. This suggests the feasibility of institutional actors using social media engagement to promote safe behaviors. We conclude by discussing how our findings may be used to develop more effective communication strategies regarding public perceptions of mask use and other relevant safety measures.

Duygu Analizi ve Metin Madenciliği ile Hizmet Kalitesi Ölçüm Modeli Önerisi: Su ve Kanalizasyon Hizmetleri Örneği

This study proposes a new model for service quality measurement using sentiment analysis and text mining techniques. This model aims to overcome traditional methods' time, cost and implementation difficulties and provide a more dynamic and efficient approach to service quality measurement. In addition, in this model, instead of the dimensions used in service quality measurements, such as SERVQUAL or SERVPERF, it is shown how to determine new categories and keywords specific to the service sector in which the model is used by text mining. Thus, it is aimed at something other than reaching more accurate results in service quality measurement. To achieve the model’s purpose, it aims to develop a service quality measurement model using social media data processed by text mining and sentiment analysis. To find an answer to this question, the keywords "flood", "meter", "rain", "irrigation", "infrastructure", "sewerage", "sewage", "maintenance hole ", "aski", "waterless", "water" were extracted from 109.844 tweets sent to the Twitter account of a municipality between 2016 and 2022 by text mining method. Service quality was measured by subjecting 5766 tweets containing the keywords extracted to sentiment analysis. As a result of the service quality measurement, 1922 negative, 973 positive and 2871 neutral tweets were identified. The average negative score was 0.51, the average positive score was 0.11, and the average neutral score was 0.38.