Number Of Tweets Research Articles

#BoycottMurree campaign on twitter: Monitoring public response to the negative destination events during a crisis

Research on how the public responds and attributes their experiences to negative destination events on social media during a crisis is limited. This study fills the research gap by analyzing public response on social media to highly visible immoral destination events and service failures. A chain of negative events took place when a heavy snow storm hit a popular tourism destination (i.e., Murree); these events were extensively publicized on Twitter, and is used as a case. Applying text mining as a combination of topic modeling and sentiment analysis to 89,897 tweets in the dataset, the study analyzes temporal and topical dynamics of public discussion to investigate the useful insights of such data at each disaster stage based on the extended Fink's four-stages of crisis and disaster model. The study shows that the public response on twitter as a number of tweets is moderated by the series of negative events. Results reveal that the majority of tweets are posted in the chronic phase. The most popular tweeted themes are related to tourists' switching intentions – and voicing, portraying negative image of Murree as a tourism destination. Further, anger has been the most dominating emotion, following fear, sadness, and joy during the crisis life cycle. Moreover, the most negative emotions expressed in Tweets relate to topics: local and international sentiments about the incidents followed by the public emotions toward crisis and negative destination image. The findings offer practical implications in tourism, hospitality, and crisis management domains having the potential for future research, which will truly offer value addition for potential researchers.

Relationship of Altmetric Attention Score, Twitter Performance, and Dimensions Badge Value With Traditional Metrics in Top-Cited Anterior Cruciate Ligament Research Studies.

Alternative citation metrics-such as the Altmetric Attention Score (AAS), number of tweets (TN), and dimensions badge value (DBV)-are emerging as new options for assessing the value of scientific works. To analyze the AAS of highly cited articles on the anterior cruciate ligament (ACL) and to assess the relationship between alternative and traditional metrics such as journal rankings and article citation performance. Cross-sectional study. A search was conducted using the Web of Science Core Collection of databases with "anterior cruciate ligament" as the search term. Full-text articles published between 2011 and 2021 were reviewed, and the top 100 cited articles were determined. The articles were analyzed by publication year, study design, research topic, journal impact factor, journal h-index, number of total citations (TC), recent citations (RC) (ie, citations in the latest 2 years), and average citation per year (ACY), as well as AAS, TN, and DBV. For articles in the top 100 list, the median TC was 160 (interquartile range [IQR], 117-561) and the median AAS was 24.50 (IQR, 1-730). A higher AAS score was achieved by articles on return to sports and anterolateral ligament (P < .05). The AAS and TN were significantly and positively correlated with the RC (r = 0.459 and P = .001; r = 0.438 and P = .001, respectively) and ACY (r = 0.363 and P = .001; r = 0.393 and P = .001, respectively). Alternative metrics were linked to traditional metrics but were not a direct representation of bibliometrics. The AAS was not correlated with TC numbers in the ACL research. Higher AAS and Twitter popularity of an article were related to receiving high-volume RC performance. The DBV represented a stronger correlation with traditional metrics than the AAS.

Analisis Sentimen Pemilu Indonesia Tahun 2024 Dari Media Sosial Twitter Menggunakan Python

The general election of Indonesia in the upcoming 2024 will be an interesting topic for social media users, especially Twitter. Currently, Twitter is very influential in building sentiment, preferences, and public politics. So that people's Tweets can be used to see a picture of public opinion. There are various opinions of Twitter users with positive, neutral and negative sentiments. However, classifying the sentiments of Twitter users requires quite a lot of time and effort due to the large number of tweets found. The large number of incoming tweets regarding the election encourages the need for a method that helps to view public opinion effectively. By providing the textblob library, Python, which is a programming language, is able to classify tweet data and can be used to answer these problems. The tweet data is preprocessed first where there are two processes in the initial data, namely the cleaning and stemming processes. After that, a sentiment analysis was carried out to find out how the results of the classification related to public opinion from the 2024 elections and classify them into three classes, namely positive, neutral and negative using Python. The results of this study show that Python performs sentiment analysis with the results of the proportion of positive class sentiments of 40%, 52% neutral and 8% negative about the 2024 elections so that it can be concluded that Python can classify tweets from Twitter so that we can identify public opinion about elections. The general public of Indonesia in 2024 will have neutral opinions tend to be positive

Investigating Public Sentiment on Laryngeal Cancer in 2022 Using Machine Learning

This study aims to investigate public sentiment on laryngeal cancer via tweets in 2022 using machine learning. We aimed to analyze the public sentiment about laryngeal cancer on Twitter last year. A novel dataset was created for the purpose of this study by scraping all tweets from 1st Jan 2022 that included the hashtags #throatcancer, #laryngealcancer, #supraglotticcancer, #glotticcancer, and #subglotticcancer in their text. After all tweets underwent a fourfold data cleaning process, they were analyzed using natural language processing and sentiment analysis techniques to classify tweets into positive, negative, or neutral categories and to identify common themes and topics related to laryngeal cancer. The study analyzed a corpus of 733 tweets related to laryngeal cancer. The sentiment analysis revealed that 53% of the tweets were neutral, 34% were positive, and 13% were negative. The most common themes identified in the tweets were treatment and therapy, risk factors, symptoms and diagnosis, prevention and awareness, and emotional impact. This study highlights the potential of social media platforms like Twitter as a valuable source of real-time, patient-generated data that can inform healthcare research and practice. Our findings suggest that while Twitter is a popular platform, the limited number of tweets related to laryngeal cancer indicates that a better strategy could be developed for online communication among netizens regarding the awareness of laryngeal cancer.

Measuring The Impact of a Twitter-Based Educational Initiative: The #EmoryNCCTweetorials Project (P7-2.005)

<h3>Objective:</h3> Analyze a Twitter-Based Educational Initiative for a Neurocritical Fellowship <h3>Background:</h3> “Tweetorials” are online tutorials published on Twitter. This style of microteaching is an innovative way to provide free, globally accessible online medication education. For trainees, authoring a Tweetorial is a novel way to distill specialized knowledge and reach a large academic audience while also receiving immediate feedback. Authoring a Tweetorial may be a way for trainees to network and engage in longitudinal conversations within the medical community. We present analytic data about the impact of our fellowship program’s Twitter teaching initiative. <h3>Design/Methods:</h3> The Twitter education project #EmoryNCCTweetorials was announced in the Summer of 2021 as optional participation for the neurocritical care fellows. Data was collected regarding the number of participating fellows and number of Tweetorials. An AI-driven platform for Twitter analytics, “Tweepsmap ®,” was utilized to analyze the number of tweets, impact, and various types of engagement from July 1, 2021 to September 28, 2022. Participants were surveyed about their opinions of writing Tweetorials and what they learned. <h3>Results:</h3> In a fifteen-month period, five of seven fellows participated in the initiative. Twenty-two Tweetorials were created by fellows, which in total garnered over 2.5 million impressions (cumulative number of views). Together the Tweetorials were retweeted (shared) over a thousand times and received nearly five thousand likes. The Tweetorials were viewed in 62 countries and most engagement was from healthcare-associated accounts (73.1%) with the remainder being characterized as students, education, science and technology and others. The fellows rated the experience positively. <h3>Conclusions:</h3> Social media-based educational initiatives are innovative strategies for teaching neurocritical care topics and may promote trainee engagement in the neurology community and have far-reaching networking effects. Further analyses are needed to investigate longitudinal participation, information retention and value-added aspects of social media education for trainees. <b>Disclosure:</b> Dr. Sigman has nothing to disclose. Dr. Pimentel has nothing to disclose. Dr. Kandiah has nothing to disclose. Dr. Lawson has nothing to disclose. Dr. Albin has received personal compensation in the range of $5,000-$9,999 for serving as an Editor, Associate Editor, or Editorial Advisory Board Member for Continuum: Life Long Learning in Neurology. Dr. Albin has received research support from American Academy of Neurology. Dr. Albin has received publishing royalties from a publication relating to health care. Dr. Albin has received personal compensation in the range of $500-$4,999 for serving as a Instructor with Resuscitation Leadership Academy.

HPV vaccine narratives on Twitter during the COVID-19 pandemic: a social network, thematic, and sentiment analysis

IntroductionThe COVID-19 pandemic has increased online interactions and the spread of misinformation. Some researchers anticipate benefits stemming from improved public awareness of the value of vaccines while others worry concerns around vaccine development and public health mandates may have damaged public trust. There is a need to understand whether the COVID-19 pandemic, vaccine development, and vaccine mandates have influenced HPV vaccine attitudes and sentiments to inform health communication strategies.MethodsWe collected 596,987 global English-language tweets from January 2019-May 2021 using Twitter’s Academic Research Product track. We determined vaccine confident and hesitant networks discussing HPV immunization using social network analysis. Then, we used a neural network approach to natural language processing to measure narratives and sentiment pertaining to HPV immunization.ResultsMost of the tweets in the vaccine hesitant network were negative in tone (54.9%) and focused on safety concerns surrounding the HPV vaccine while most of the tweets in the vaccine confident network were neutral (51.6%) and emphasized the health benefits of vaccination. Growth in negative sentiment among the vaccine hesitant network corresponded with legislative efforts in the State of New York to mandate HPV vaccination for public school students in 2019 and the WHO declaration of COVID-19 as a Global Health Emergency in 2020. In the vaccine confident network, the number of tweets concerning the HPV vaccine decreased during the COVID-19 pandemic but in both vaccine hesitant and confident networks, the sentiments, and themes of tweets about HPV vaccine were unchanged.ConclusionsAlthough we did not observe a difference in narratives or sentiments surrounding the HPV vaccine during the COVID-19 pandemic, we observed a decreased focus on the HPV vaccine among vaccine confident groups. As routine vaccine catch-up programs restart, there is a need to invest in health communication online to raise awareness about the benefits and safety of the HPV vaccine.

Migrants vs. stayers in the pandemic – A sentiment analysis of Twitter content

In this paper, we propose a sentiment analysis of Twitter data focused on the attitudes and sentiments of Polish migrants and stayers during the pandemic. We collected 9 million tweets and retweets between January and August 2021, and analysed them using MultiEmo, the multilingual, multilevel, multi-domain sentiment analysis corpus. We discovered that the sentiment of tweets differs between migrants and stayers over time, and it relates to the country of migration. The general sentiment is similar for migrants and stayers, but a more detailed analysis reveals that hashtags related to staying safe and staying at home, as well as vaccinations are more polarised for migrants than for stayers, and they reflect the general development trend of the pandemic in Europe. In addition to comparing migrants with stayers, we also compared migrants staying in different countries. amongst the countries of migration, for which we collected at least 3000 tweets, the most positive sentiment of Polish migrants’ tweets was observed in Belgium, with the most negative sentiment coming from Estonia. We also observed that the sentiment of tweets written in Polish by stayers in Poland is less negative when compared to Polish migrants in most of the countries with the highest number of tweets.

Technology enabled communication during COVID 19: analysis of tweets from top ten Indian IT companies using NVIVO.

The corona virus (COVID-19) pandemic has impacted industries across the globe. Lockdown was imposed to curb the spread of the deadly virus. This resulted in closure of the factories and manufacturing units. Few sectors switched to work from home (WFH) for the first time. The present study aims to understand and analyze the way in which Information Technology (IT) sector communicated on Twitter during the pandemic. The top ten IT companies in India were selected on the basis of net sales. Qualitative data analysis was employed to extract tweets, understand and analyze them. Tweets were extracted from the official Twitter handles of these top ten IT companies using N-Capture extension tool of NVivo 12 software from April 1, 2020 to April 30, 2021. To get insights out of collected data, Word Cloud, TreeMap and Sentiment Analysis of tweets were carried out using NVivo 12 software. The research found that IT companies focussed on digital transformation, business development, customer satisfaction and enriching customer experience, new product development for healthcare and insurance and organizational resilience. They also focussed on effective communication through Twitter in times of crisis. Most of the companies tweeted moderately positive. Very small numbers of tweets were found to be very negative.

Relationship between university students’ emotional expression on tweets and subjective well-being: Considering the effects of their self-presentation and online communication skills

This study investigated how personal characteristics such as generalized trust, self-consciousness and friendship, and desire for self-presentation are related to the subjective well-being of university students who use Twitter in Japan, including the effects of their online communication skills. We conducted a survey in May 2021 with Twitter users and analyzed their log data between January 2019 and June 2021. The log data of 501 Twitter users, including the number of public tweets, retweets, and emotional expressions among different patterns of social media (e.g., Twitter only, Twitter + Instagram, Twitter + LINE + Instagram, etc.) and academic standings, were analyzed using ANOVA and stepwise regression analyses. The results showed that the number of tweets and retweets, with and without photos/videos, increased in 2020 and 2021 compared to 2019, and the ratio of positive sentences remained almost the same for the two-and-a-half-year period of this study. However, the proportion of negative sentences increased slightly. It is clear that the factors which affected the university students’ subjective well-being differed depending on the respective patterns of social media use.

Optimizing sentiment analysis of Nigerian 2023 presidential election using two-stage residual long short term memory

Sentiment analysis is the process of recognizing positive or negative attitudes in text. This technique makes use of computational linguistics, text analysis, and natural language processing. The 2023 presidential election in Nigeria is a significant event for the country, as it will determine the leader of the nation for the next four years. As such, it is important to understand the sentiment of the public towards the different candidates. In this research, we aimed to understand the sentiment of the public towards the three main candidates in the 2023 presidential election in Nigeria, Atiku, Tinubu, and Obi, by conducting a sentiment analysis on tweets related to the candidates. We used the long short-term memory (LSTM), peephole long short term memory (PLSTM), and two-stage residual long short-term memory (TSRLSTM) models to classify tweets as positive, neutral, or negative. Our dataset consisted of a large number of tweets that were preprocessed to remove noise and irrelevant information. Results showed that TSRLSTM performed excellently well in classifying the tweets and in identifying the sentiment towards each candidate individually. Our findings provide valuable insights into the public's opinion on the candidates and their campaign strategies, which can be useful for researchers, political analysts, and decision-makers. Our study highlights the importance of sentiment analysis in understanding public opinion and its potential applications in the field of political science.

Detecting Hate Speech and Offensive Language using Machine Learning in Published Online Content

Businesses are more concerned than ever about hate speech content as most brand communication and advertising move online. Different organisations may be incharge of their products and services but they do not have complete control over their content posted online via their website and social media channels, they have no control over what online users post or comment about their brand. As a result, it became imperative in our study to develop a model that will identify hate speechand, offensive language and detect cyber offence in online published content using machine learning. This study employed an experimental design to develop a detection model for determining which agile methodologies were preferred as a suitable development methodology. Deep learning and HateSonar was used to detect hate speech and offensive language in posted content. This study used data from Twitter and Facebook to detect hate speech. The text was classified as either hate speech, offensive language, or both. During the reconnaissance phase, the combined data (structured and unstructured) was obtained from kaggle.com. The combined data was stored in the database as raw data. This revealed that hate speech and offensive language exist everywhere in the world, and the trend of the vices is on the rise. Using machine learning, the researchers successfully developed a model for detecting offensive language and hate speech on online social media platforms. The labelling in the model makes it simple to categorise data in a meaningful and readable manner. The study establishes that in fore model to detect hate speech and offensive language on online social media platforms, the data set must be categorised and presented in statistical form after running the model; the count indicates the total number of data sets imported. The mean for each category, as well as the standard deviation and the minimum and maximum number of tweets in each category, are also displayed. The study established that preventing online platform abuse in Zambia requires a comprehensive approach that involves government law, responsible platform policies and practices, as well as individual responsibility and accountability. In accordance with this goal, the research was effective in developing the detection model. To guarantee that the model was completely functional, it was trained on the English dataset before being applied to the local language dataset. This was because of the fact that training deep learning models with local datasets can present a number of challenges, such as limited, biased data, data privacy, resource requirements, and model maintenance. However, the efficacy of these systems varies, and there have been concerns raised about the inherent biases and limitations of automatic moderation techniques. The study recommends that future studies consider other sources of information such as Facebook, WhatsApp, Instagram, and other social media platforms, as well as consider harvesting local data sets for training machines rather than relying on foreign data sets; the local data set can then be used to detect offences targeting Zambian citizens on local platforms.

Fossil fuel companies' climate communication strategies: Industry messaging on renewables and natural gas

Research shows that multinational oil and gas companies have recently made a strategic shift away from outright climate denial to more nuanced discourses of climate delay. Communication on social media is an under-analyzed part of the fossil fuel industry's strategy to delay the energy transition away from fossil fuels to a renewable future. This study examines how four companies (Shell, ExxonMobil, BP, and TotalEnergies) are communicating about the renewable transition by analyzing tweets published by their global Twitter accounts. Each of these companies tweets about different renewable technologies in the context of showcasing their own renewable projects. TotalEnergies and BP focus mostly on solar, ExxonMobil on biofuels, and Shell on hydrogen; geothermal and hydropower are hardly mentioned by any of the companies. The number of tweets mentioning renewables increased rapidly after 2015. Topic modeling on tweets about renewables shows that renewables are often mentioned together with natural gas, emphasizing how both are essential for emissions reductions. Similarly, computational text analysis on tweets about natural gas reveals how companies highlight the social good of natural gas including promoting its role in emissions reductions, presenting natural gas as a fuel for a cleaner future, and emphasizing that natural gas is critical to meeting growing societal demand for energy. This pattern of communication - linking renewables to natural gas and promoting natural gas as part of their corporate response to climate change - suggests an evolution of fossil fuel companies' strategic efforts to delay the energy transition and obstruct climate action.

Twitter-Based Disaster Response Using Machine Learning

Twitter, a microblogging platform, receives real-time information via informal conversations, and it has, accordingly, become the main source of data for research studies based on emergency situational awareness. Millions of tweets are posted on Twitter every day, and during disasters, the frequency of tweets relating to an on-going crisis event grows exponentially. This unprecedented increase in the number of tweets during disasters needs to be monitored, identified, processed, and analyzed so that necessary measures can be taken at the earliest to reduce the loss or damage during emergencies. However, due to large voluminous data being available during crisis hours, it is almost impossible for a human to perform these tasks in real time. In this regard, a semi-automated AI-based disaster response system for Twitter data is proposed. The proposed disaster response system would be capable of extracting essential situational awareness information related to a disaster and would also be capable of sketching tentative area of critically affected population.

ArHateDetector: detection of hate speech from standard and dialectal Arabic Tweets

Hate speech has become a phenomenon on social media platforms, such as Twitter. These websites and apps that were initially designed to facilitate our expression of free speech, are sometimes being used to spread hate towards each other. In the Arab region, Twitter is a very popular social media platform and thus the number of tweets that contain hate speech is increasing rapidly. Many tweets are written either in standard, dialectal Arabic, or mix. Existing work on Arabic hate speech are targeted towards either standard or single dialectal text, but not both. To fight hate speech more efficiently, in this paper, we conducted extensive experiments to investigate Arabic hate speech in tweets. Therefore, we propose a framework, called arHateDetector, that detects hate speech in the Arabic text of tweets. The proposed arHateDetector supports both standard and several dialectal Arabic. A large Arabic hate speech dataset, called arHateDataset, was compiled from several Arabic standard and dialectal tweets. The tweets are preprocessed to remove the unwanted content. We investigated the use of recent machine learning and deep learning models such as AraBERT to detect hate speech. All classification models used in the investigation are trained with the compiled dataset. Our experiments shows that AraBERT outperformed the other models producing the best performance across seven different datasets including the compiled arHateDataset with an accuracy of 93%. CNN and LinearSVC produced 88% and 89% respectively.

Tweets Emotions Analysis of Community Activities Restriction as COVID-19 Policy in Indonesia Using Support Vector Machine

With the rising number of COVID-19 cases in Indonesia, the government has implemented the Imposition of Restrictions on Emergency Community Activities (Pemberlakuan Pembatasan Kegiatan Masyarakat - PPKM) as Indonesia’s COVID-19 policy. Several controversies and protests have colored the implementation of this emergency policy. Some netizens on Twitter voice their opinions about the policy in their tweets. Emotions in tweets can be recognized through text-based emotion detection or emotion analysis. However, textbased emotion detection is a challenging task. One of the main issues in classifying text with a machine learningbased approach deals with the feature dimensions. As a result, appropriate methods for accurately identifying emotion based on the text are required. The research studies an emotions analysis task on Indonesians’ PPKMrelated tweets to understand their emotional state while implementing the PPKM. The machine learning classification algorithms used are Support Vector Machine (SVM) and random forest. The total number of tweets is 4,401. The results show that SVM with linear kernel function combined with the TF-IDF and Chi-Square methods outperforms other classifiers with an accuracy of 0.7528. The accuracy value is higher than those obtained by previous studies. Moreover, the results of the emotion classification on PPKM tweets reveal that most Indonesians are unhappy with the implementation of the PPKM policy.

Identifying the challenges and opportunities of PCOS awareness month by analysing its global digital impact.

Although significant resources are invested each September for PCOS Awareness Month campaign, there are no studies measuring its impact. We evaluated the digital impact of PCOS Awareness Month, common themes and associated topics, top influencers, and global equity of influence during the PCOS Awareness month. In this serial cross-sectional analysis, we studied the outputs from Symplur® to study the total impressions of #PCOS on Twitter®. We tracked the hashtags-#PCOS, #PCOSawarenessmonth, #PCOSawareness-and a search query- "#PCOS OR #PCOSawarenessmonth OR #PCOSawareness"-using Sproutsocial® to study the total number of tweets related to PCOS Awareness Month. Network analysis was done using SocioViz® to identify common themes and associated topics. Using SymplurRank® machine learning algorithm, the top 10 #PCOS influencers were identified based on the number of mentions received. Google® Trends was used to study the web and news search popularity over the last 10 years beyond social media platforms. An overall upward trend in the digital impact of PCOS awareness was noted since 2017. While the top themes associated with PCOS (insulin resistance, depression, anxiety, menopause, hormones, infertility) remained the same in 2021 and 2022, newer themes emerged in the latter year suggesting the need for ongoing review. News outlets were the most influential organisations during PCOS Awareness Month in both years of study. Seven of the top 10 users were the same in both years. Limited engagement from African, Asian, South American, and non-English speaking European countries was seen on Google Trends analysis. Active involvement from various stakeholders of PCOS Awareness Month has shaped it into an effective strategy to raise awareness with social media playing a crucial role in amplifying the message. Our findings also provide an opportunity to understand the current perceptions and expectations amongst the public, which can influence future healthcare investment and research.

Twitter-Based Sentiment Analysis and Topic Modeling of Social Media Posts using Natural Language Processing, to Understand People’s Perspectives Regarding COVID-19 Omicron Subvariants XBB.1.5 and BF.7

Concerns about an increase in cases during the COVID-19 pandemic have been heightened by the emergence of a new Omicron subvariant XBB.1.5 that joined the previously reported BF.7 as a source of public health concern. COVID-19 cases have been on the rise intermittently throughout the ongoing pandemic, likely because of the continuous introduction of SARS-CoV-2 subtypes. The present study analyzed the Indian citizen’s perceptions of the latest covid variants XBB.1.5 and BF.7 using the natural language processing technique, especially topic modeling and sentiment analysis. The tweets posted by Indian citizens regarding this issue were analyzed and used for this study. Government authorities, policymakers, and healthcare officials will be better able to implement the necessary policy effectively to tackle the XBB 1.5 and BF.7 crises if they are aware of the people’s sentiments and concerns about the crisis. A total of 8,54,312 tweets have been used for this study. Our sentiment analysis study has revealed that out of those 8,54,312 tweets, the highest number of tweets (n = 3,19,512 tweets (37.3%)) about COVID variants XBB.1.5 and BF.7 had neutral sentiments, 3,16,951 tweets (37.1%) showed positive sentiments and 2,17,849 tweets (25.4%) had negative sentiments. Fear of the future and concerns about the immunity of the vaccines are of prime concerns to tackle the ongoing pandemic.

Sentiment Analysis of Tweets on Soda Taxes.

As a primary source of added sugars, sugar-sweetened beverage (SSB) consumption may contribute to the obesity epidemic. A soda tax is an excise tax charged on selling SSBs to reduce consumption. Currently, 8 cities/counties in the United States have imposed soda taxes. This study assessed people's sentiments toward soda taxes in the United States based on social media posts on Twitter. We designed a search algorithm to systematically identify and collect soda tax-related tweets posted on Twitter. We built deep neural network models to classify tweets by sentiments. Computer modeling. Approximately 370 000 soda tax-related tweets posted on Twitter from January 1, 2015, to April 16, 2022. Sentiment associated with a tweet. Public attention paid to soda taxes, indicated by the number of tweets posted annually, peaked in 2016, but has declined considerably ever since. The decreasing prevalence of tweets quoting soda tax-related news without revealing sentiments coincided with the rapid increase in tweets expressing a neutral sentiment toward soda taxes. The prevalence of tweets expressing a negative sentiment rose steadily from 2015 to 2019 and then slightly leveled off, whereas that of tweets expressing a positive sentiment remained unchanged. Excluding news-quoting tweets, tweets with neutral, negative, and positive sentiments occupied roughly 56%, 29%, and 15%, respectively, during 2015-2022. The authors' total number of tweets posted, followers, and retweets predicted tweet sentiment. The finalized neural network model achieved an accuracy of 88% and an F1 score of 0.87 in predicting tweet sentiments in the test set. Despite its potential to shape public opinion and catalyze social changes, social media remains an underutilized source of information to inform government decision making. Social media sentiment analysis may inform the design, implementation, and modification of soda tax policies to gain social support while minimizing confusion and misinterpretation.

Polarity-Based Sentiment Analysis of Georeferenced Tweets Related to the 2022 Twitter Acquisition

Twitter, one of the most important social media platforms, has been in the headlines regularly since its acquisition by Elon Musk in October 2022. This acquisition has had a strong impact on the employees, functionality, and discourse on Twitter. So far, however, there has been no analysis that examines the perception of the acquisition by the users on the platform itself. For this purpose, in this paper, we use georeferenced Tweets from the US and classify them using a polarity-based sentiment analysis. We find that the number of Tweets about Twitter and Elon Musk has increased significantly, as have negative sentiments on the subject. Using a spatial hot spot analysis, we find distinct centres of discourse, but no clear evidence of their significant change over time. On the West Coast, however, we suspect the first signs of polarisation, which could be an important indication for the future development of discourse on Twitter.

To Tweet or not to Tweet? The Determinants of Tweeting Activity in Initial Coin Offerings

AbstractOur research explores the causes of Twitter activity in highly technological start‐ups that finance their activities via initial coin offerings (ICOs). By relying on weekly data of 297 ICOs for the period 2015–2020 (35,459 observations), we examine how major exogenous events affect the number of tweets issued by the start‐up. Then, we explore how the community of followers reacts to the tweets. We discover that events external to firms reduce ICOs’ tweeting activity. Moreover, our evidence indicates that the followers’ reaction is positively related to the tweets issued by the firm and negatively related to major events unrelated to the firm. Interestingly, followers’ reaction has an inverted U‐shaped relation with the firm's Twitter volume, suggesting that excessive Twitter activity can harm the further dissemination of tweets. Our results, robust to alternative estimation techniques, emphasize the important role of Twitter as an information disseminator, legitimizer, and endorser for highly opaque firms.