Twitter Analysis Research Articles

SA-MSVM: Hybrid Heuristic Algorithm-based Feature Selection for Sentiment Analysis in Twitter

One of the drastically growing and emerging research areas used in most information technology industries is Bigdata analytics. Bigdata is created from social websites like Facebook, WhatsApp, Twitter, etc. Opinions about products, persons, initiatives, political issues, research achievements, and entertainment are discussed on social websites. The unique data analytics method cannot be applied to various social websites since the data formats are different. Several approaches, techniques, and tools have been used for big data analytics, opinion mining, or sentiment analysis, but the accuracy is yet to be improved. The proposed work is motivated to do sentiment analysis on Twitter data for cloth products using Simulated Annealing incorporated with the Multiclass Support Vector Machine (SA-MSVM) approach. SA-MSVM is a hybrid heuristic approach for selecting and classifying text-based sentimental words following the Natural Language Processing (NLP) process applied on tweets extracted from the Twitter dataset. A simulated annealing algorithm searches for relevant features and selects and identifies sentimental terms that customers criticize. SA-MSVM is implemented, experimented with MATLAB, and the results are verified. The results concluded that SA-MSVM has more potential in sentiment analysis and classification than the existing Support Vector Machine (SVM) approach. SA-MSVM has obtained 96.34% accuracy in classifying the product review compared with the existing systems.

Role of Social Media in Technology Adoption for Sustainable Agriculture Practices: Evidence from Twitter Analytics

Social networking sites provide a new means of communication for disseminating cutting-edge agricultural technologies. These are unmediated interaction channels that enable a user to communicate their experience with technology and generate negative or positive attitudes that impact technology adoption decisions. We employ a machine learning approach to analyse users' existing semantic predisposition for technology adoption in agriculture at various operational levels. While developing attitudes toward technology adoption, these semantic tendencies become an important aspect of users' cognitive decision making. The study scrapes user comments and conversations about agritech on Twitter through data mining. The research also explains the important characteristics that enhance attitude building on Twitter and are responsible for reinforcing decision making among information seekers using four machine learning models. Based on the results, the research recommends strategies to managers for better communication with agriculturists and enhancement of users' decision making.

Twitter Data Analysis Using Hadoop and ‘R’ and Emotional Analysis Using Optimized SVNN

Standalone systems cannot handle the giant traffic loads generated by Twitter due to memory constraints. A parallel computational environment provided by Apache Hadoop can distribute and process the data over different destination systems. In this paper, the Hadoop cluster with four nodes integrated with RHadoop, Flume, and Hive is created to analyze the tweets gathered from the Twitter stream. Twitter stream data is collected relevant to an event/topic like IPL- 2015, cricket, Royal Challengers Bangalore, Kohli, Modi, from May 24 to 30, 2016 using Flume. Hive is used as a data warehouse to store the streamed tweets. Twitter analytics like maximum number of tweets by users, the average number of followers, and maximum number of friends are obtained using Hive. The network graph is constructed with the user’s unique screen name and mentions using ‘R’. A timeline graph of individual users is generated using ‘R’. Also, the proposed solution analyses the emotions of cricket fans by classifying their Twitter messages into appropriate emotional categories using the optimized support vector neural network (OSVNN) classification model. To attain better classification accuracy, the performance of SVNN is enhanced using a chimp optimization algorithm (ChOA). Extracting the users’ emotions toward an event is beneficial for prediction, but when coupled with visualizations, it becomes more powerful. Bar-chart and wordcloud are generated to visualize the emotional analysis results.

The Recognition of the Authocephaly of the Macedonian Orthodox Church–Archdiocese of Ohrid and Reflections by the Public: A Twitter Analysis

The Recognition of the Authocephaly of the Macedonian Orthodox Church–Archdiocese of Ohrid and Reflections by the Public: A Twitter Analysis

Attitudes towards Afghan refugees and immigrants in Turkey: A Twitter analysis

Data generated by social media platforms such as Twitter provide a unique opportunity to examine large-scale public communication produced spontaneously and in real-time, and consequently, contribute to comprehensively understanding the complex set of attitudes towards refugees. The present study utilises a qualitative approach to explore host members’ attitudes towards refugees on social media during the global crisis. In particular, we examine perceptions of a broader population, Twitter users, and analyse public reactions towards Afghan refugees expressed within tweets during the pandemic in Turkey as a response to the 2021 Afghan refugee influx. We analysed and coded 2,686 tweets using qualitative content analysis based on four main categories: 1) Representations of Afghan refugees and immigrants, 2) main causes for rejecting them, 3) taking action against them and their supporters, and 4) positive attitudes towards them. Results highlighted the prevalence of negative perceptions about, dehumanisation of, and racism towards Afghan refugees in Turkey mainly due to perceived realistic, symbolic, demographic, security, moral, and health threats from them. However, the findings also showed there were positive, albeit very few, attitudes towards Afghan refugees in the form of solidarity, help and empathy. We discuss these findings in relation to the existing literature on host society members’ attitudes towards refugees and immigrants and why we need to qualitatively examine these attitudes on social media.

Gender Identification Using Marginalised Stacked Denoising Autoencoders on Twitter Data

Gender analysis of Twitter could reveal significant socio-cultural differences between female and male users. Efforts had been made to analyze and automatically infer gender formerly for more commonly spoken languages’ content, but, as we now know that limited work is being undertaken for Arabic. Most of the research works are done mainly for English and least amount of effort for non-English language. The study for Arabic demographic inference like gender is relatively uncommon for social networking users, especially for Twitter. Therefore, this study aims to design an optimal marginalized stacked denoising autoencoder for gender identification on Arabic Twitter (OMSDAE-GIAT) model. The presented OMSDAE-GIAR technique mainly concentrates on the identification and classification of gender exist in the Twitter data. To attain this, the OMSDAE-GIAT model derives initial stages of data pre-processing and word embedding. Next, the MSDAE model is exploited for the identification of gender into two classes namely male and female. In the final stage, the OMSDAE-GIAT technique uses enhanced bat optimization algorithm (EBOA) for parameter tuning process, showing the novelty of our work. The performance validation of the OMSDAE-GIAT model is inspected against an Arabic corpus dataset and the results are measured under distinct metrics. The comparison study reported the enhanced performance of the OMSDAE-GIAT model over other recent approaches.

Negativity spreads faster: A large-scale multilingual twitter analysis on the role of sentiment in political communication

Social media has become extremely influential when it comes to policy making in modern societies, especially in the western world, where platforms such as Twitter allow users to follow politicians, thus making citizens more involved in political discussion. In the same vein, politicians use Twitter to express their opinions, debate among others on current topics and promote their political agendas aiming to influence voter behaviour. In this paper, we attempt to analyse tweets of politicians from three European countries and explore the virality of their tweets. Previous studies have shown that tweets conveying negative sentiment are likely to be retweeted more frequently. By utilising state-of-the-art pre-trained language models, we performed sentiment analysis on hundreds of thousands of tweets collected from members of parliament in Greece, Spain and the United Kingdom, including devolved administrations. We achieved this by systematically exploring and analysing the differences between influential and less popular tweets. Our analysis indicates that politicians’ negatively charged tweets spread more widely, especially in more recent times, and highlights interesting differences between political parties as well as between politicians and the general population.

A Machine Learning-Based Technique with Intelligent WordNet Lemmatize for Twitter Sentiment Analysis

Laterally with the birth of the Internet, the fast growth of mobile strategies has democratised content production owing to the widespread usage of social media, resulting in a detonation of short informal writings. Twitter is microblogging short text and social networking services, with posted millions of quick messages. Twitter analysis addresses the topic of interpreting users’ tweets in terms of ideas, interests, and views in a range of settings and fields. This type of study can be useful for a variation of academics and applications that need knowing people’s perspectives on a given topic or event. Although sentiment examination of these texts is useful for a variety of reasons, it is typically seen as a difficult undertaking due to the fact that these messages are frequently short, informal, loud, and rich in linguistic ambiguities such as polysemy. Furthermore, most contemporary sentiment analysis algorithms are based on clean data. In this paper, we offers a machine-learning-based sentiment analysis method that extracts features from Term Frequency and Inverse Document Frequency (TF-IDF) and needs to apply deep intelligent wordnet lemmatize to improve the excellence of tweets by removing noise. We also utilise the Random Forest network to detect the emotion of a tweet. To authenticate the proposed approach performance, we conduct extensive tests on publically accessible datasets, and the findings reveal that the suggested technique significantly outperforms sentiment classification in multi-class emotion text data.

TWITTER COMO HERRAMIENTA PARA LA MONITORIZACIÓN DE ACTITUDES: EL USO ESTRATÉGICO DE LAS REDES SOCIALES

This research delves into Twitter analysis, a well-known social media messaging service recently acquired by Elon Musk for $44bn, which we argue to enable researchers to better monitor (and try to solve) the status of the general population regarding the type of user and content of the received messages. With this analysis, it is intended to show the possibility of disseminating reliable, immediate, and high-quality messages (that would be unlikely obtained through official information channels), potentially provoking in this way an exponential impact afterwards. This idea in particular is key, due to any average social media population user and especially from 'Gen Z' (which hold 25% lower attention capacity and 40% lower check of the reliability of sources than its predecessor generation) could easily understand wrongly the massive (and unfiltered) amounts of information received, therefore generating false alarms, beliefs and in some cases, even own welfare losses. To do so, along this paper we propose the development of a pedagogical activity with a multi-methodological approach through which to carry out a qualitative (and cross-sectional) analysis in the degree of ‘Business Administration and Management’ of EDEM-Business School. Thus, the aforementioned activity would constitute a successful teaching innovation exercise as regards to the acquisition of the required competencies and learning outcomes established within the course, as well as to the achievement of a (attainable and consensual) solution to a real problem faced nowadays and selected by the students: in this case, the increase of awareness about the cervical cancer, a type of cancer that is currently the fourth most common among women worldwide and one of the easiest to prevent through screening tests.

2366. Impact of the Febrile Podcast and Learning Resource as an Infectious Diseases Education Platform

Abstract Background Febrile is a digital infectious diseases (ID) learning platform with the aim of providing high quality and accessible ID content. We describe utilization of Febrile as a resource for learning and teaching ID, learner satisfaction, and the perceived impact on clinical practice. Methods Febrile was launched in December 2020 as a trainee-focused resource as shown in Figure 1. Content is also promoted on social media. Podcast analytics are available from the media host, Captivate, which is Interactive Advertising Bureau certified. Website and Twitter engagement was obtained from Google and Twitter Analytics, respectively. An online anonymous survey was conducted to assess educational impact using Likert scales and open answer questions. Results As of April 26 2022, Febrile has produced 39 episodes and has been downloaded > 107,000 times in all 50 United States (US) and 140 countries. Majority of the audience (62%) listens from within the US, see Fig. 2 for geographic distribution. The website has received > 60,000 views, and the Twitter account has garnered > 8,100 followers. A total of 224 participants from 30 countries and 37 US states completed the survey, of whom 78 (35%) were ID fellows in training and 71 (32%) were ID faculty physicians. Breakdown of other respondents is in Fig. 3. Most had listened to either ≥ 21 episodes (57, 25%) or 11–20 episodes (86, 38%). In addition, 72% reported visiting the website and 82% had seen a Febrile infographic. There was a high level of satisfaction with the resources, and 83% of respondents have already recommended Febrile to a colleague (Fig. 3). Enhancing core ID knowledge was the primary driver for listening among other reasons noted in Fig. 4. Two-thirds of respondents indicated that information they learned from Febrile has changed their practice, and 50% have used Febrile as a way to teach others (Fig. 4). Of note, for those considering ID as a career, Febrile had a favorable impact on perception of the specialty (30/34, 88%). Many respondents also indicated Febrile as a source of community (50%, Fig. 4 and 5). Conclusion Febrile is a novel and impactful tool for ID medical education. In addition to providing educational resources, this innovative digital platform holds the potential for meaningful community building and attracting trainees to the field of ID. Disclosures All Authors: No reported disclosures.

1347. @Women_in_ID : A Social Media Platform for Advocacy and Amplification of Women in Infectious Diseases

Abstract Background In 2015, 39.7% of active infectious diseases (ID) physicians in USA were women. This calculation does not include the many other women professionals in ID such as Advanced Practice Providers, ID pharmacists, researchers in ID and Infection Preventionists. There is no dedicated national platform for women in ID and no Twitter representation of groups dedicated to women in ID. Women in Infectious Disease (WIID) with twitter handle @Women_in_ID was created April 22nd 2021, for women providers in ID to collaborate, promote, and advocate for each other through a social media platform; and to highlight significant issues like gender pay gap, inequity in career advancement and leadership, research funding etc. We sought to explore the social media impact of this account over the last year. Methods A descriptive content analysis of this account from April 2021 to May 1st, 2022 was done to reflect on lessons learned, plan future directions, and highlight some real-world changes that happened after creation of WIID. Twitter analytics were used, and manual review of followers’ accounts and tweet activities were done to assess engagement. Results In 12 months, this account has gained 1709 followers (Image 1). Out of the followers, 109 are twitter accounts of organizations, such as fellowship programs, ID societies and their foundations, ID divisions, and journals. The rest appear to be individuals. Since demographics of followers are not revealed in twitter accounts, this could not be assessed. Table 1 provides detailed twitter analytics and content that got the most engagement each month. During the month of September, the account highlighted 20 nominated profiles (including women from other countries), and several other women in ID with significant historical contributions (Image 2). This content resulted in our highest engagement and new members. Some previously unnoticed women in history had Wikipedia pages created after their work was amplified. Image 1:Women in ID (WIID) twitter profile pageImage 2:Women in Medicine Month call for nominations created to amplify women in ID Conclusion @Women_in_ID is the first and only twitter platform dedicated for women in ID. This platform is accessible to every woman in ID with a twitter account, hence networking, amplification and collaboration transcends local or institutional boundaries. In future, social media work must translate to real life changes to have meaningful impact. Disclosures All Authors: No reported disclosures.

Sentiment Analysis of Twitter's Opinion on The Russia and Ukraine War Using BERT

Sentiment Analysis of Twitter's Opinion on The Russia and Ukraine War Using BERT

Sentiment Analysis of Twitter's Opinion on The Russia and Ukraine War Using Bert

News about the war that took place between Russia and Ukraine can not be denied affecting various aspects of life in the world. This affects the writings of every citizen of the world on various social media platforms, one of which is Twitter. Sentiment analysis is a process of identifying and making sentiment categories which is done computationally. Sentiment analysis process is also intended to make computers understand the meaning of sentences written by humans by processing using algorithms. This study uses a deep learning method using a language model, namely BERT (Bidirectional Encoder Representation Form Transformers) as a process of analyzing the sentiments that exist in tweets written about the war in Russia and Ukraine by twetter social media users. These sentiments will be divided into three parts, namely positive, neutral and negative. In this study, the hyperparameters used were 10 epochs, learning rate 2e-5, and batch size 16. The sentiment analysis test used the BERTbase Multilingual-cased-model model and the accuracy value obtained was 97%.

Twitter Analysis of Pseudoarchaeology and Conspiracy Theories in Archaeology

General understanding of archaeology arises from mainstream news and entertainment alongside academia. However, there is increasing concern over the presence of pseudoarchaeology and related conspiracies among the mainstream public, especially on social media. Online engagement can draw greater public support and attention for pseudoarchaeological claims. In this paper, I approach Tweets about several archaeological conspiracies through network analysis. Network analyses facilitate broader study of discourse and the relationships between topics in a conversation. By looking at the larger picture of archaeology in combination with specific Tweet examples, I characterize pseudoarchaeological engagement and affiliation within Twitter. I find that pseudoarchaeology related Tweets employ anti-institutional sentiment and draw on rhetorical themes in support of a historical white supremacy. Pseudoarchaeology and conspiracy on Twitter detract from the goals of archaeological research and breed harmful notions about ancient and modern Indigenous populations.

Cochrane Skin Group's Global Social Media Reach: Content Analysis of Facebook, Instagram, and Twitter Posts.

Researchers in all medical specialties increasingly use social media to educate the public, share new publications with peers, and diversify their audiences. Given Cochrane Skin Group's expanded use of social media in the past years, we aimed to characterize Cochrane Skin Group's international social media audience and identify themes that result in increased content engagement. Cochrane Skin Group's Facebook, Instagram, and Twitter analytics data were extracted for follower demographics and the most viewed posts within a 3-year span (June 2019 to June 2022). Overall, Cochrane Skin Group had the highest number of followers on Facebook (n=1037). The number of Instagram and Twitter followers reached 214 and 352, respectively. The greatest numbers of Facebook followers were from Brazil, Egypt, and India, with 271, 299, and 463 followers, respectively. Facebook's most viewed post about Cochrane Skin Group's annual meeting received 1041 views. The top post on Instagram, which introduced Cochrane Skin Group's social media editors, received 2522 views. Each of the social media platforms used by Cochrane Skin Group reached varying audiences all over the world. Across social media platforms, posts regarding Cochrane Skin Group meetings, members, and professional opportunities received the most views. Overall, Cochrane Skin Group's multiplatform social media approach will continue to grow an international audience, connecting people interested in skin disease.

Sentiment Analysis Terhadap Tulisan Mengenai Universitas Pertamina Di Media Sosial Twitter

Nowadays, branding is not only applied to business sectors. Many universities have implemented branding to maintain the university's brand image so that it can attract prospective students. Sentiment analysis is one of the activities to monitor the university’s brand image in the community. This research applies a machine learning approach to conduct a social media analysis of Twitter. The dataset consists of 4323 tweets containing the word ”Universitas Pertamina”. Each tweet is then grouped into three different classes based on the tweet's sentiment, namely negative, neutral and positive. This study uses three types of machine learning models: Convolutional Neural Network (CNN), Long Short Term Memory (LSTM) and CNN-LSTM. The procedure for the three models uses the stratified 5-fold cross-validation technique. Model performance is then measured using a learning curve and measuring parameters such as accuracy, weighted-f1 and balanced accuracy. The CNN-LSTM model records the highest accuracy value, 76.92% and the highest weighted-f1 with 76.78%. Meanwhile, the LSTM model gets the highest balanced accuracy value with 66.05%.

To wear or not to wear? Unpacking the #NoMask discourses and conversations on Twitter

In the context of the COVID-19 health crisis, the use of face masks has been a topic broadly debated. In many Western countries, especially at the heights of the pandemic, discussions on the use of protective facemasks were often linked to what were mainly political considerations, often fueled by health-related misinformation. Our study brings together social sciences and computer science expertise to retrospectively unpack the #NoMask discourses and conversations using both network analysis approaches on big data retrieved from Twitter and qualitative analyses on sub-sets of relevant social media data. By looking comparatively at two dataset gathered at different stages of the health crisis (2020 and 2022), we aim to better understand the role of Twitter in that interesting area where the dissemination of health misinformation became capitalized by the political narrative linking the social discontent caused by the socio-economic impacts of the pandemic to specific political ideologies. Our analyses show that there has never been a unique ‘NoMask movement,’ nor a defined online community. Rather, we can identify a range of relatively niche, loosely connected, and heterogeneous actors that, in the course of the pandemic, independently pushed diverse (but converging and compatible) discourses. Conversations directly linked to the #NoMask relevant hashtags are overall limited, as twitters using them are not talking to each other; nonetheless, they successfully engaged a larger audience.

The First Year of Hematology Oncology Fellows -- a Social Media Community for Hematology/Oncology Trainees

Background: While resources exist to address the needs of graduate medical trainees, online resources to assist trainees with specialty-specific professional development have not been fully developed or described in the past. The Hematology-Oncology Fellows Network (@HemOncFellows) is an online community for hematology-oncology trainees in all stages of training, including medical students, residents, fellows, and doctoral students. The network's goals are to provide professional development in hematology-oncology, create a community and safe space for hematology-oncology trainees, and amplify the voices and needs of trainees. In addition, the network is contributing to educational development of fellows by conducting twitter spaces, which are informal discussions on twitter, educational and professional development. Methods: The Hem Onc Fellows community was founded in February of 2021. Demographics of newsletter subscribers were gathered, and qualitative and quantitative analysis was performed. Twitter analytics data was used to see the outreach and engagement with the @hemoncfellows twitter account. Results: Since its inception, the Hem-Onc Fellows Network has grown to more than 3400 followers. The highest impressions per month have been 93.4K with mean twitter 263 impressions per tweet in the month of July 2022. The mean engagement per tweet was 3.4%. The network hosts Twitter Spaces (TS) with guests every two weeks and distributes a newsletter. During the first season, 22 TS were held between July 2021 and June 2022. The average attendance of twitter spaces is 49.6 persons per session (range 22-187). The most popular twitter spaces events were pre ASH and pre ASCO special events. The hem-onc fellows network contributed to two professional development opinions in ASH hematopoiesis and two in ASCO connections. One hundred twenty-one people subscribed to the newsletter. 53% of subscribers were male. 34% were internal medicine residencies, 31% were hematology-oncology fellows, 9% were attendings, 5% were Advanced Hematology-Oncology Fellow and 5% were medical students. Subscribers were from 21 different countries. Most participants were United States-based, but there were participants from 21 countries worldwide. Conclusions: We demonstrate that implementing a trainee network on Twitter attracted participation and engagement from a diverse pool of trainees worldwide. TS represents a novel educational tool for engaging trainees and facilitating professional development. We expect further expansion and engagement continuing to the season two of hem-onc fellows network Figure 1View largeDownload PPTFigure 1View largeDownload PPT Close modal

An Overall Analysis of Twitter and Elon Musk M&A Deal

In April 2022, the investor of Tesla and SpaceX, Elon Musk, start the acquisition of the social media platform, Twitter. Elon Musk offers $44 billion ($54.20 per share) to purchase Twitter. However, this M&A deal faced an impasse in July 2022. This deal is ending with Twitter having sued Elon Musk to ‘force’ the completion of the $44 billion purchase which causes this deal seems will be failed. The paper focuses on the financial deal between two powerful parties, the social media platform Twitter and the richest man alive Elon Musk (by 2022), by illustrating whilst analyzing the various strategic tactics and methodology displayed by each individual party towards achieving their objectives, in order to finally be able to interpret the whole timeline of the deal. The projection that both parties' BATNA will be when this deal fails fully will also be explained at the conclusion of this paper.

Netflix's communication strategy on Twitter and Instagram during the unlock in Spain: humour, proximity and information

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