Platform Twitter Research Articles

Analysis of flows in social media uncovers a new multi-step model of information spread

Abstract Since the advent of the internet, communication paradigms have continuously evolved, resulting in a present-day landscape where the dynamics of information dissemination have undergone a complete transformation compared to the past. In this study, we challenge the conventional two-step flow communication model, a long-standing paradigm in the field. Our approach introduces a more intricate multi-step and multi-actor model that effectively captures the complexities of modern information spread. We test our hypothesis by examining the spread of information on the Twitter platform. Our findings support the multi-step and multi-actor model hypothesis. In this framework, influencers (individuals with a significant presence in social media) emerge as new central figures and partially take on the role previously attributed to opinion leaders. However, this does not apply to opinion leaders who adapt and reaffirm their influential position on social media, here defined as opinion-leading influencers. Additionally, we note a substantial number of adopters directly accessing information sources, suggesting a potential decline in influence in both opinion leaders and influencers. Finally, we found distinctions in the diffusion patterns of left-/right-leaning groups, indicating variations in the underlying structure of information dissemination across different ideologies.

Influence of social media and the digital environment on international migration of health workforce from low- and middle-income countries post COVID-19 pandemic: a scoping review protocol

IntroductionMigration of the health workforce from low- and middle-income countries (LMCIs) is increasingly becoming a phenomenon of interest within migration governance systems. The COVID-19 pandemic aggravated health workforce shortages that...

The Influence of Service Quality and Customer Satisfaction on Customer Loyalty of BCA Mobile in Bandar Lampung

PT. Bank Central Asia, Tbk, founded in 1957, is one of the largest private banks in Indonesia today with an asset value of 1,408 trillion rupiah with a net profit of 48.6 trillion rupiah. The results of the Bank Service Excellence Monitor (BSEM) survey conducted by Marketing Research Indonesia (MRI) in the 2020-2021 edition produced data that BCA Mobile was ranked second and the 2023-2024 edition was ranked fifth in the 10 best mobile banking performances in Indonesia. The problem in this research is that there has been a decline in BCA Mobile's performance followed by many complaints about the use of the BCA Mobile application, which has become a trending topic on the X social media platform (Twitter). BCA Mobile must attention to this so that customers do not think about looking for alternatives to other mobile banking. The aim of this research is to test whether service quality and customer satisfaction have an influence on BCA Mobile customer loyalty in Bandar Lampung City. This research uses a survey method by distributing questionnaires to 90 respondents via Google Form. The analytical method used is simple regression using the partial test (t test) and Sobel test with the SPSS 25 application. The results of the research show that the service quality variable and customer satisfaction variable have an influence on the BCA Mobile customer loyalty variable in Bandar Lampung City.

Entity Linking for real-time geolocation of natural disasters from social network posts.

When a fast kinetic natural disaster occurs, it is crucial that crisis managers quickly understand the extent of the situation, especially through the development of "big picture" maps. For many years, great efforts have been made to use social networks to help build this situational awareness. While there are many models for automatically extracting information from posts, the difficulty remains in detecting and geolocating this information on the fly so that it can be placed on maps. Whilst most of the work carried out to date on this subject has been based on data in English, we tackle the problem of detecting and geolocating natural disasters from French messages posted on the Twitter platform (now renamed "X"). To this end, we first build an appropriate dataset comprised of documents from the French Wikipedia corpus, the dataset from the CAp 2017 challenge, and a homemade annotated Twitter dataset extracted during French natural disasters. We then developed an Entity-Linking pipeline in adequacy with our end-application use case: real-time prediction and peak resiliency. We show that despite these two additional constraints, our system's performances are on par with state-of-the-art systems. Moreover, the entities geolocated by our model show a strong coherence with the spatiotemporal signature of the natural disasters considered, which suggests that it could usefully contribute to automatic social network analysis for crisis managers.

Unsupervised detection of coordinated fake-follower campaigns on social media

Automated social media accounts, known as bots, are increasingly recognized as key tools for manipulative online activities. These activities can stem from coordination among several accounts and these automated campaigns can manipulate social network structure by following other accounts, amplifying their content, and posting messages to spam online discourse. In this study, we present a novel unsupervised detection method designed to target a specific category of malicious accounts designed to manipulate user metrics such as online popularity. Our framework identifies anomalous following patterns among all the followers of a social media account. Through the analysis of a large number of accounts on the Twitter platform (rebranded as X after the acquisition of Elon Musk), we demonstrated that irregular following patterns are prevalent and are indicative of automated fake accounts. Notably, we found that these detected groups of anomalous followers exhibited consistent behavior across multiple accounts. This observation, combined with the computational efficiency of our proposed approach, makes it a valuable tool for investigating large-scale coordinated manipulation campaigns on social media platforms.

Public Participation Monitoring: Social Media Data Mining and Analysis of User Engagement Patterns

Social Media Platforms (SMP) like Twitter and Facebook have become public influencing medium in today’s digital age which facilitate community interactions. These necessitates the monitoring of public participation in these SMP. This work performs such an study by examining the user engagement patterns in social media in Indonesia during the national elections (#Pemilu2024), Ramadan celebrations (#Ramadan2024), and climate change discussions (#ClimateChange). The data for the study was collected during a period of six months from (January to June 2024) using event-specific hashtags and keywords. To identify the user engagement patterns datamining and Natural Language Processing (NLP) tools were utilized. The findings show that the Twitter platform has higher user engagement in morning with news updates and visual updates at evening. The Facebook show user engagement in afternoon with videos and evening engagement with shared articles. The Sentiment Analysis (SA) and network analysis was performed over the dataset and the findings have shown that higher positive sentiments towards elections and Ramadan but argumentative towards climate change discussions. The Twitter show rapid communication effectiveness compared to Facebook. Further the youth prefer faster update and older expect detailed content sharing.

STRATEGI BRANDING POLITIK DI ERA MEDIA SOSIAL TWITTER: ANALISIS KEBERHASILAN BRANDING JOKOWI-MA’ARUF AMIN PADA PILPRES 2019

This study aims to analyze the political branding strategy used by the Jokowi-Ma'ruf Amin winning team in the 2019 Presidential Election, especially through the Twitter platform. Amid various religious issues and criticisms of the Jokowi regime's performance, Jokowi-Ma'ruf's electability had decreased. Therefore, the winning team must design an appropriate communication strategy to restore the positive image of the candidate pair. This study uses a qualitative descriptive approach with the help of NVivo 12 Plus software to analyze content from Twitter. The focus of the analysis includes political brand equity indicators, namely brand association, brand loyalty, and brand awareness. The results of the study show that Jokowi-Ma'ruf Amin's political branding strategy is more dominated by brand association and brand loyalty, which reached 42.67% and 36.67%, respectively. Brand association plays an important role in building Jokowi-Ma'ruf's personal branding through the support of political parties such as PDI-P and PKB, while brand loyalty can be seen from the strong support of modernist and traditional Islamic groups such as Nahdlatul Ulama (NU). On the other hand, brand awareness does not contribute significantly to branding strategy, with only 19.33% of the total analysis results. This study highlights the importance of managing brand association and brand loyalty in forming an effective political image on social media

TWEETING BETWEEN THE LINES: EXPLORING CODE MIXING IN THE TWITTERSPHERE

Communication is the most essential thing in purpose. In life, sometimes we communicate with people who speak different languages from ours. Moreover, it could be an obstacle to the process of communication in society. In everyday life, we often use code-mixing with the aim of making the person immediately understand what we say. Code-mixing is the practice of combining two or more languages or language varieties within a single conversation, sentence, or even word. This research aims to analyze code-mixing phenomena in the Twittersphere. This research focused on recognizing the types of code-mixing and factors influencing code-mixing by Twitter users. This study uses a descriptive qualitative research design. The subject of this study is Twitter users who post tweets that contain code-mixing. The researcher uses documentation as a data collection method. The data for identifying the types of code-mixing were collected by documentation, such as the tweets posted previously by Twitter users on the Twitter platform.

Sentiment Analysis Towards the Film Dirty Vote on Twitter Social Media Using the K-Nearest Neighbor Algorithm

The appearance of the dirty vote film has received public attention and went viral on social media after being released and watched by millions of people in a short time. The dirty vote film has become a topic of discussion, one of which is on the social media platform Twitter. This research was conducted to determine the views or tendencies of public opinion regarding dirty vote films on Twitter social media using K-Nearest Neighbor which will be classified into positive, neutral and negative sentiment. The sentiment data that was collected in the data crawling process was 4000 pieces of data. Then after preprocessing there were 3978 data. Labeling was carried out using text blob, it was found that the negative sentiment class was 3470 superior to the positive sentiment class of 451 and the neutral sentiment class was 57. The 10-fold cross validation test produced an average accuracy value of 87.5%. Testing was carried out with 80% training data consisting of 3182 data and 20% test data consisting of 796 test data. The results of sentiment analysis show that the K-Nearest Neighbor method can be used for sentiment analysis. The accuracy value obtained was 87%, precision was 87%, recall was 100%, and f1-score was 93%.

Mapping the discursive landscape of data activism: Articulations and actors in an emerging movement

Growing awareness of the societal consequences of datafication in recent years has given rise to a new form of civil society engagement called data activism. This article examines the discourse surrounding data activism on the social media platform Twitter. Through a mixed-methods approach combining computational analysis of Twitter content and close readings of Twitter profiles, we explore how new forms of civil society action related to data justice are articulated and linked to other forms of activism, conflicts and problems, and the actors involved in these articulations. Our analysis reveals a distinction between two articulatory patterns in the data activism discourse. The first involves grassroots actors, such as community organisations and individual citizens, who challenge existing power structures and advocate for social change. The second, on the other hand, is associated with academics, capitalists and policymakers who already hold positions of power and influence. This asymmetry is consistent with previous findings in data activism research. We encourage future research to extend these patterns, using additional methods and case studies, to further refine and contextualise the understanding of data activism within the civil society realm.

Greek Tweets on Long COVID: Topic Modelling Following Sentiment Analysis and ChatGPT Interpretation.

Long COVID is a disease that makes it hard for patients to get an official diagnosis while it impacts their quality of life. Many people are turning to social networks such as Facebook, WhatsApp, Twitter (now X) to express their opinions and feelings regarding Long COVID. In this paper, positive (or neutral) and negative text messages in the Greek language, posted on the Twitter platform in 2022, regarding Long COVID are analyzed and popular discussion topics are extracted. Analysis revealed that when topic modelling follows sentiment analysis more coherent topics are created. Furthermore, ChatGPT is used to assign a label to each topic that, in turn, is assessed by a human expert.

Analyzing public sentiment toward economic stimulus using natural language processing

PurposeThis study aims to investigate public sentiment toward economic stimulus using textual analysis. Specifically, it analyzes Twitter’s public opinion, emotion-based sentiment and topics related to COVID-19 economic stimulus packages.Design/methodology/approachThis study applies natural language processing techniques, such as sentiment analysis, t-distributed stochastic neighbor embedding and semantic network analysis, to a global data set of 88,441 tweets from January 2020 to December 2021 extracted from the Twitter platform, discussing COVID-19 economic stimulus packages.FindingsResults show that in the fourth quarter of 2021, there is a declining trend of positive sentiment (−5%) and an increasing trend of negative sentiment (14%), which may indicate the perceived inadequacy of COVID-19 stimulus measures. Topic modeling identifies seven topics, highlighting the necessity of stimulus in the education sector.Practical implicationsThe big-data findings of this study provide a better understanding of public sentiment about economic stimulus for regulators and policymakers, which can help in formulating more effective fiscal and monetary policies.Originality/valuePublic sentiment is a significant concern for regulators because of its associated ambiguity, such as how to design stimulus packages and evaluate the effectiveness of previous measures. This study applies natural language processing, contributing to the growing literature on designing effective economic stimulus.

Improving the application and assessment experiences of special constable candidates in England and Wales

PurposeThis paper proposes a set of recommendations based upon the limitations found with the application and assessment process to become a Special Constable (SC) with one of the 43 police forces in England and Wales.Design/methodology/approachParticipants were recruited via online social media platforms Twitter and LinkedIn, as well as personal networks and the study was geared towards both respondents who had completed the whole of the application and assessment process, as well as those who may have withdrawn at a particular point or who failed an element of the assessment.FindingsThis study yielded several key findings. First, some respondents had limited to no knowledge of the role of the Special Constable, nor of the depth of police work that would be expected of them. Secondly, respondents indicated that they would have benefited from support during the application and assessment process, specifying the advantages that could be derived from a variety of sources such as local force input and workshop sessions. Finally, respondents stated that poor communication from recruiting teams impacted their experience of applying to the Special Constable programmes, causing them to rethink their decision to join.Originality/valueThis research proposes that a far greater input from serving Special Constables during the application and assessment process is key to improving the experiences of candidates, and to their chances of success with the programme.

ANALISIS SENTIMEN KEPUASAN PELAYANAN TRANSPORTASI ONLINE GOJEK MENGGUNAKAN ALGORITMA EXTREME LEARNING MACHINE

With the rapid advancement of technology, online transportation has become the main solution for many people in Indonesia to travel easily and efficiently. Companies such as GOJEK are constantly innovating to improve their services, resulting in many responses and reviews from users. This research aims to analyze customer satisfaction with these online transportation services by analyzing the sentiment of user opinions on the Twitter platform. Sentiment analysis plays a very important role in decision making by classifying user reviews. Data was retrieved through a crawling process using specific keywords related to each service. The data preprocessing process includes case folding, tokenizing, normalization, stemming, filtering, and convert negation. This aims to clean and prepare the data so that it can be processed using the algorithm better. This process includes removing irrelevant elements from the text data, converting the text into a consistent or more standardized form, reducing the number of features in the data by stemming, and converting the text into numbers or vectors so that it can be processed by the algorithm. Feature extraction is performed using the Word2Vec model to convert text into a numerical vector representation that can later be processed by ELM. Converts words into numeric vectors in a high-dimensional space, where words that have the same context in the text are close to each other in that space. The ELM (Extreme Learning Machine) algorithm is used as a classification model due to its high training speed and good generalization ability. Model evaluation is done using confusion matrix which measures classification performance through accuracy, precision, recall matrix. The results of this study show that the ELM algorithm with Word2Vec feature extraction is able to classify user sentiment with a high level of accuracy. This research provides insight into user satisfaction with online transportation services and can be a reference for companies to improve their service quality

Unveiling evolving nationalistic discourses on social media: a cross-year analysis in pandemic

The global pandemic has dramatically reshaped public discourse, with social media emerging as a pivotal platform for these discussions. This study delves into evolving sentiments, emotions, and prevalent topics in online discussions spanning the years 2020, 2021, and 2022, drawing from a dataset of 2.65 million tweets from the Twitter Platform. A multifaceted approach that combines quantitative and qualitative methods are developed for dissecting evolving discourses, with a particular focus on the lens of nationalism. The quantitative part disassembling sentiment & emotion, topics, and Co-Occurrence Network yields a nuanced understanding of the textual content. A qualitative theoretical analysis named Evolving Discourse Framework Analysis are designed to unravel the textual discourse. Study results in the development of an adaptable framework. Findings expose nationalist orientations and the framing elements present within online public discourse, which are categorized into three distinct frames: ‘feeling,’ ‘identity,’ and ‘action.’ Importantly, the ‘feeling’ frame interconnects with the ‘identity’ frame, ultimately shaping responses within the ‘action’ frame. The frames shine a light on a complex and interconnected web of nationalist narratives that exist within the online sphere, subtly influencing public opinion and behavior. This study serves as a reminder that beneath the surface of seemingly unified global discourse, there exists a segmented world, ripe for further exploration and understanding.

Kontribusi Platform Digital Sosial Terhadap Peningkatan Ketertarikan Siswa pada Perguruan Tinggi Baru di Indonesia

Universities as institutions providing educational services must be able to adapt to this. Currently, there are many universities that use social media, but not many universities can make optimal use of social media. Promotion is something that every company must do. The main thing in promotion is to create a persuasive message that is effective to attract the attention of consumers. The use of social media for prospective new students. This study aims to decipher the influence of social media use on the number of new students. This research is a quantitative descriptive research. The sample was taken from users of 9 digital platforms Youtube, Facebook, Tik Tok, Instagram, Twitter, Sportify, ClubHouse, Pintrest and Linkedin. Based on the results of the research, the use of digital platforms to increase the number of university students is increasing. This paper seeks to outline how the trend of social media use in universities, what social media platforms can be used in universities and how social informatics is the use of digital social media platforms for universities.

Educational policy in times of war 2022: A case study of the Twitter of the Ministry of Education and Science in Poland

The aim of the conducted research was to analyze the activity of the Polish Ministry of Education and Science on Twitter and to diagnose and then describe the perspective (experiences, reflections, postulates) of Twitter users, thus enabling the analysis and evaluation of activities undertaken in the field of shaping education policy in times of Russian aggression to Ukraine. The subject of the research were entries and comments posted on the Twitter platform on the account of the Polish Ministry of Education and Science in Poland placed in the time period from February 24, 2022 (the first day of Russia’s invasion of Ukraine) to June 1, 2022 (celebration related to Children’s Day). The collected data were analyzed in the MAXQDA program in accordance with the prepared – described in detail in the article – code key. As part of the research, a total of 259 posts and 2,339 comments were analyzed. It turned out that Twitter users are reluctant to create recommendations (3% of all entries), while the vast majority of comments contain negative opinions and experiences related to education policy. The analysis also showed a worrying trend towards an increasing number of hate speech comments. Users often used the Twitter platform to mock politicians, but also made statements directed against the Ukrainian people. Based on the conducted research, it is extremely difficult to describe the activities undertaken in the field of education policy by the Polish Ministry of Education and Science. It should be noted that the analyzed entries in most cases are only very short messages, often referring only to visits or speeches by politicians. At the same time, it is worth emphasizing that comments posted by users rarely enter into substantive polemics, because they are usually only a vent for very negative emotions.

Using Social Media to Understand Primary Discussions in Gastrointestinal Cancers: Machine Learning Approach.

The incidence and mortality rates of gastrointestinal (GI) cancers are high in the United States as well as worldwide. The widespread use of social media provides unique opportunities to facilitate the dissemination of information, especially in the context of health. We aim to characterize the public's primary discussions, including perceptions, concerns, and interests toward GI cancers, from prevention, diagnosis, and treatment to survivorship care through the social media platform Twitter, using tweets posted by Twitter users. We analyzed 87 860 Twitter posts related to GI cancers. We used machine learning with natural language processing to identify salient topics and themes in the collected tweets. The most common themes across all GI cancer types included cancer risk prevention and awareness outreach programs, risk factors including lifestyles (primarily diet), and cancer survivorship-related discussions (primarily GI symptoms and quality of life). GI symptom-related tweets were prevalent in patients with colorectal and stomach cancers, whereas themes of newer clinical trials, end-of-life trials, palliative care trials, and disease prognosis were common in tweets related to liver/biliary and pancreatic cancers. Our research emphasizes the importance of individualized approaches in managing GI cancers, considering lifestyle and diet, the need for comprehensive survivorship care, raising awareness, delivering information, and improving targeted interventions related to GI cancers. Our study suggests utilizing Twitter data to better understand the real-world interest and concerns about GI cancers among the public, which can guide future patient-centered research in this field.

The Usage of Twitter (Now 𝕏) Amplifiers in the European Elections of 2019

The aim of this study is to investigate how amplifiers are used in Twitter (now called “X”) during election campaigns. Specifically, the main purpose is to identify the role and engagement of Twitter amplifiers in the 2019 European elections, the visibility of political parties and leaders, and the way in which automated tools are used to manipulate public opinion by influencing voting decisions. The countries considered in the study are two economic powers of Western Europe, France and Germany, as well as two countries of the European South, which are affected by the economic and financial crisis, Greece and Italy. The countries from Southern Europe were included in the sample as they are often used by mass media as political campaign tools. This paper emphasizes the Twitter platform through which the data collection was implemented using the official API of the social networking tool, focusing on the 2019 European elections. We collected data on 88 party leaders and MEP candidates between 10 May and 30 May 2019, as well as on 44,651 accounts that retweeted them. We concluded using 237,813 election-related tweets and used network theory to analyze and visualize the data. The results demonstrate that all political parties use amplifiers to promote their tweets, and some use the same amplifiers between different countries.

*Corresponding author: suwandi.sumartias@unpad.ac.id E-ISSN: 2289-1528 https://doi.org/10.17576/JKMJC-2024-4002-01 Portrait of Hate Speech Propagators' Behaviour in Indonesia Twittersphere: A Comparative Virtual Ethnography Study

Political life in Indonesia today cannot be separated from the social media platform Twitter (X) because it is often used to express opinions freely. Unfortunately, a handful of parties misused the freedom of communication and expression offered by Twitter (X) to spread hate speech. One of the biggest phenomena is “Cebong” and “Kadrun”. This research examines the characteristics of hate speech spreaders in the political context of "Cebong" and "Kadrun". This study employed virtual ethnography to interpret the phenomenon of political hate speech on Twitter (X) in May 2022. The hate speech made by "Cebong" and "Kadrun" can be concluded as two hostile political camps. They argued with each other to show their identity as supporters of one of the camps and aimed to bring down the opposing political camp. The tweets made by “Cebong” were dominated by arguments classified as arguments by analogy; meanwhile, "Kadrun" was dominated by discovery arguments: arguments from cause to effect. The manipulation strategy carried out by "Cebong" is dominated by connotations, and "Kadrun" is dominated by specific warrants and connotations. The fallacy expressed by "Cebong" is dominated by persuasive definitions; meanwhile, "Kadrun" is dominated by hasty generalizations. These findings could be suggestions for creating a healthier ecosystem in the digital public sphere in Indonesia. Twitter (X) users should be more aware of reporting content that indicates hate speech. By knowing the characteristics of hate speech and the characteristics of hate speech spreaders, Twitter users can stop the spread of hate speech. Keywords: Cebong, Kadrun, hate speech, propagators, Twitter.