Twitter Users Research Articles

Sentiment Analysis of Twitter Users Towards the Kartu Prakerja Program Using the Naive Bayes Method

This study conducts a sentiment analysis of Twitter users regarding the Indonesian government’s Kartu Prakerja program, utilizing the Naive Bayes method for classification. Launched in 2020 to enhance employability skills amidst the COVID-19 pandemic, the program has garnered various public responses. A total of 836 tweets containing the keyword "Kartu Prakerja" were collected using the Twitter API and analyzed to determine sentiment distribution. Results indicate a predominance of neutral sentiment (800 tweets), with only 17 positive and 22 negative tweets. The Naive Bayes method achieved an accuracy of 95%, demonstrating its effectiveness in sentiment classification. However, comparisons with other methods, such as Support Vector Machine (SVM) and Recurrent Neural Network (RNN), reveal that these techniques yield higher accuracy rates (98.34% and 96%, respectively). This research highlights the importance of sentiment analysis in understanding public perceptions and informs policymakers about areas needing improvement. The findings underscore the potential of integrating advanced machine learning techniques to enhance sentiment analysis and provide insights into the effectiveness of government programs like Kartu Prakerja.

The offline roots of online hostility: Adult and childhood administrative records correlate with individual-level hostility on Twitter

Reducing hostility in social media interactions is a key public concern. Most extant research emphasizes how online contextual factors breed hostility. Here, we take a different perspective and focus on the offline roots of hostility, that is, offline experiences and stable individual-level dispositions. Using a unique dataset of Danish Twitter users (N [Formula: see text] 4,931), we merge data from administrative government registries with a behavioral measure of online hostility. We demonstrate that individuals with more aggressive dispositions (as proxied by having many more criminal verdicts) are more hostile in social media conversations. We also find evidence that features of childhood environments predict online hostility. Time spent in foster care is a strong correlate, while other indicators of childhood instability (e.g., the number of moves and divorced parents) are not. Furthermore, people from more resourceful childhood environments-those with better grades in primary school and higher parental socioeconomic status-are more hostile on average, as such people are more politically engaged. These results offer an important reminder that much online hostility is rooted in offline experiences and stable dispositions. They also provide anuanced view of the core group of online aggressors. While these individuals display general antisocial personality tendencies by having many more criminal verdicts, they also come from resourceful backgrounds more often than not.

Analysis of Software Developers' Programming Language Preferences and Community Behavior From Big5 Personality Traits

ABSTRACTMany programming languages and technologies have appeared for the purpose of software development. When choosing a programming language, the developers' cognitive attributes, such as the Big5 personality traits (BPT), may play a role. The developers' personality traits can be reflected in their social media content (e.g., tweets, statuses, Q&A, reputation). In this article, we predict the developers' programming language preferences (i.e., the pattern of picking up a language) from their BPT derived from their content produced on social media. We randomly collected data from a total of 820 Twitter (currently X) and Stack Overflow (SO) users. Then, we collected user features (i.e., BPT, word embedding of tweets) from Twitter and programming preferences (i.e., programming tags, reputation, question, answer) from SO. We applied various machine learning (ML) and deep learning (DL) techniques to predict their programming language preferences from their BPT. We also investigated other interesting insights, such as how reputation and question‐asking/replying are associated with the users' BPT. The findings suggest that developers with high openness, conscientiousness, and extraversion are inclined to mobile applications, object‐oriented programming, and web programming, respectively. Furthermore, developers with high openness and conscientiousness traits have a high reputation in the SO community. Our ML and DL techniques classify the developers' programming language preferences using their BPT with an average accuracy of 78%.

Psychological underpinnings of partisan bias in tie formation on social media.

Individuals preferentially reciprocate connections with copartisans versus counter-partisans online. However, the mechanisms underlying this partisan bias remain unclear. Do individuals simply prefer viewing politically congenial content, or do they additionally prefer socially connecting with copartisans? Is this driven by preference for in-party ties or distaste for out-party ties? In a Twitter (now called X) field experiment, we created bot accounts varying by partisanship and whether they identified as bots or humans. We randomly assigned Twitter users (N = 3,013) to be followed by one of these accounts. We found evidence for social motivation-users were much more likely to reciprocate links to copartisan relative to counter-partisan accounts when the accounts identified as humans versus bots. We also found evidence for both in-party preference and out-party dispreference-users were as likely to follow back copartisan accounts as they were unlikely to followback counter-partisan accounts, compared to politically neutral accounts. A follow-up survey experiment (N = 990) provides further evidence for distinct roles of issue polarization, out-party animosity, and in-party affinity in moderating follow-back decisions online. (PsycInfo Database Record (c) 2024 APA, all rights reserved).

Y/N and OOMFs: Development, Maintenance, and Consequences of Parasocial Relationships on Stan Twitter

The study examines Stan Twitter users’ sense of belonging and their likelihood of creating PSRs as a substitute for real-life connections lost due to the COVID-19 pandemic. A convergent mixed-method design: specifically, the parallel databases variant was used to test the hypothesis and explore research questions. Conducted in January 2022, the study involved online interviews via Zoom with participants from the Philippines. Participants included Stan Twitter users (N = 126) and non-Stan Twitter users (N = 111), all at least 18 years old. Additionally, qualitative interviews were conducted with Stan Twitter users (N = 12) to explore PSRs in depth. Quantitative results (t = 0.548; p = 0.584) indicate no significant difference in the need to belong between the samples; Pandemic (i.e., period) and generational (i.e., Gen Z) effects are seen as contributors. Qualitative results show that PSRs develop due to fulfillment of belongingness needs and other factors, are maintained through parasocial interactions and fandom activities, and have both negative and positive implications for stans’ relationships, fandom behavior, personal growth, and well-being. The findings suggest reinforcing cybersecurity measures and potentially redefining PSRs due to their perceived reciprocation.

Do political elite endorsements influence online mobilization? A study of Twitter behavior in Narendra Modi’s 2019 election campaigns

ABSTRACT Modern campaigns increasingly rely on social media to influence voters, with Twitter offering affordances that enable direct communication between politicians and the public. However, scholars remain divided over the effectiveness of engaging ordinary Twitter users for mobilizing support online. This article seeks to address this issue by examining whether endorsements from political elites influence the tweeting behavior of ordinary users. Using a quasi-experimental design, we analyze an original dataset of tweets made by users who were mentioned (N = 27,634; 36.62 million tweets) and not mentioned (N = 27,672; 16.30 million tweets) by Indian Prime Minister Narendra Modi on 16th March 2019, during his national election campaign. Our analysis reveals that, on average, users mentioned by Modi exhibited a greater increase in tweet activity compared to those not mentioned. However, this surge in activity proved to be only temporary, suggesting that mentions by political elites facilitate immediate mobilization but are not necessarily self-sustaining. Furthermore, no evidence was found of a differential effect based on users’ pre-existing engagement levels. Our findings offer important insights into political leaders’ strategic use of Twitter in campaigns and contribute to the theoretical understanding of Twitter's role in mobilization and interactivity by bringing in diverse perspectives from the Global South.

Comparison of Pre-Defined Automatic Machine Learning (AutoML) for MBTI Personality Prediction of Twitter Users using Binary Classification Approach

The Myers-Briggs Type Indicator (MBTI) is a personality test that is globally accepted and used as a method for identifying personality. MBTI uses a four-factor linear model to characterize a person's behaviour patterns. This feature is often used to pursue career opportunities, make decisions, manage leadership, and deal with stress. In particular, MBTI personality prediction has been widely conducted and well performed using Recurrent Neural Network (RNN) based on Twitter data because it indirectly reveals most of a person's personality through their tweets. However, deep understanding is needed in building RNN-based solutions. Hence it will take a lot of time and resources to produce an excellent model architecture and the parameters used. Therefore, this study proposed the Auto Machine Learning (AutoML) method with a pre-defined search space to determine the correct model architecture and hyperparameters based on the results of data analysis. Thus, the search algorithm can exploit environments with suitable configurations in general. There are two pre-defined search spaces employed in this study, i.e. (i) two RNN algorithms, including Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU), and (ii) pre-trained Word2Ves as word embedding. In addition, this study compares the model's performance that employs preprocessing and raw data (without preprocessing). The first result shows that the preprocessing increases the F1-Score values for LSTM and GRU by 2.35% and 2.02%, respectively. Subsequently, the LSTM outperformed GRU by the values of F1-Score at 0.35% and accuracy at 0.76%. The implementation of LSTM with pre-processed data in pre-defined AutoML with Word2Vec as a word embedding technique can provide good performance on long and complex data sequences such as Twitter data for predicting its user personality.

What Are the Most Popular Articles in Urogynecology and Who Is Disseminating Them

Importance This research describes which articles published in Urogynecology are garnering the most attention online. Understanding which articles are having the largest impact in the online community has become increasingly important due to the exponential increase in the use of social media on the internet. Objective The Altmetric Attention Score (AAS) is a quantitative and qualitative measure of the articles’ online attention in social media and news outlets, blogs, and reference managers. The aim of this study was to provide an analysis of those accessing and sharing the 100 most popular articles published in Urogynecology. Study Design This was a retrospective descriptive analysis. Using Dimensions, a “linked research knowledge system,” data about each article’s demographics on Twitter and other media sources was extracted from each of the articles within Urogynecology with the highest AAS. No articles were excluded. The articles were categorized by topic and metrics of online sharing were compared among categories. Results Fifteen categories were created. Sexual health and education articles had the highest average Altmetric scores per article and reached the highest impressions per article and had the highest average follower count per Twitter user. On average, social justice in medicine had the highest number of tweets per article. Tweets were most often composed by members of the public (58%) compared with health care practitioners (14%), researchers (13%), and science communicators (12%). Conclusions Sexual health and education articles had the highest average AAS and impressions on Twitter. We observed a difference in which articles are being shared most among the general public and health care professionals. The general public comprised a majority of those sharing articles online regardless of category. Additionally, there may be a disparity in research, its funding, and online scientific communications within the field of urogynecology.

Assessment of beliefs and attitudes towards benzodiazepines using machine learning based on social media posts: an observational study

BackgroundBenzodiazepines are frequently prescribed drugs; however, their prolonged use can lead to tolerance, dependence, and other adverse effects. Despite these risks, long-term use remains common, presenting a public health concern. This study aims to explore the beliefs and opinions held by the public regarding benzodiazepines, as understanding these perspectives may provide insights into their usage patterns.MethodsWe collected public tweets published in English between January 1, 2019, and October 31, 2020, that mentioned benzodiazepines. The content of each tweet and the characteristics of the users were analyzed using a mixed-method approach, including manual analysis and semi-supervised machine learning.ResultsOver half of the Twitter users highlighted the efficacy of benzodiazepines, with minimal discussion of their side effects. The most active participants in these conversations were patients and their families, with health professionals and institutions being notably absent. Additionally, the drugs most frequently mentioned corresponded with those most commonly prescribed by healthcare professionals.ConclusionsSocial media platforms offer valuable insights into users’ experiences and opinions regarding medications. Notably, the sentiment towards benzodiazepines is predominantly positive, with users viewing them as effective while rarely mentioning side effects. This analysis underscores the need to educate physicians, patients, and their families about the potential risks associated with benzodiazepine use and to promote clinical guidelines that support the proper management of these medications.Clinical trial numberNot applicable.

Racial Minorities Face Discrimination From Across the Political Spectrum When Seeking to Form Ties on Social Media: Evidence From a Field Experiment.

We conducted a preregistered field experiment examining racial discrimination in tie formation on social media. We randomly assigned research accounts varying on race (Black, White) and politics (liberal/Democrat, conservative/Republican, neutral) to follow a politically balanced sample of Twitter (i.e., X) users (N = 5,951) who were unaware they were in a research study. We examined three predictions from the social and political psychology literatures: i) individuals favor White over Black targets, ii) this tendency is stronger for conservatives/Republicans than for liberals/Democrats, and iii) greater discrimination by conservatives/Republicans is explained by the assumption that racial minorities are liberal/Democrat. We found evidence that individuals were less likely to reciprocate social ties with Black accounts than White accounts. However, this tendency was not moderated by individuals' political orientation, shared partisanship, or partisan mismatch. In sum, this work provides field experimental evidence for racial discrimination in tie formation on social media by individuals across political backgrounds.

Tweeting, talking, or doing politics? Testing the influence of communication on democratic engagement

Being politically and civically engaged is known to benefit society. Using online forums, such as Twitter (the social media platform now known as X), for democratic engagement is now commonplace. However, research is inconclusive on whether offline and online activities similarly result in real-world engagement. Using secondary analysis of Pew data, both types of engagement are compared among Twitter users. Results show Twitter users engaged online, but not offline. However, those who posted about political/social issues democratically engaged both offline and online.

Mental health and the Covid-19 pandemic: main topics published in Portuguese and Italian on Twitter

Aim: Analyze published topics about mental health and the Covid-19 pandemic in public posts in Portuguese and Italian on Twitter. Methodology: Study of qualitative, cross-sectional approach, developed from the analysis of public Twitter posts in Portuguese and Italian language about mental health and the Covid-19 pandemic. The data were extracted, transcribed and the content were analyzed from Thematic Analysis. Results: A total of 430 Twitter posts were analyzed and five categories were created: Diverse criticisms about behavior and public policies; Restrictions and privations; The (in)attention to mental health care; Burnout, exhaustion, and emotional overload and Impact of the pandemic on education. Conclusion: The analyses showed impacts in different spheres of life of Twitter users in both countries, mainly in aspects related to mental health care in the virtual environment.

Differences in misinformation sharing can lead to politically asymmetric sanctions.

In response to intense pressure, technology companies have enacted policies to combat misinformation1-4. The enforcement of these policies has, however, led to technology companies being regularly accused of political bias5-7. We argue that differential sharing of misinformation by people identifying with different political groups8-15 could lead to political asymmetries in enforcement, even by unbiased policies. We first analysed 9,000 politically active Twitter users during the US 2020 presidential election. Although users estimated to be pro-Trump/conservative were indeed substantially more likely to be suspended than those estimated to be pro-Biden/liberal, users who were pro-Trump/conservative also shared far more links to various sets of low-quality news sites-even when news quality was determined by politically balanced groups of laypeople, or groups of only Republican laypeople-and had higher estimated likelihoods of being bots. We find similar associations between stated or inferred conservatism and low-quality news sharing (on the basis of both expert and politically balanced layperson ratings) in 7 other datasets of sharing from Twitter, Facebook and survey experiments, spanning 2016 to 2023 and including data from 16 different countries. Thus, even under politically neutral anti-misinformation policies, political asymmetries in enforcement should be expected. Political imbalance in enforcement need not imply bias on the part of social media companies implementing anti-misinformation policies.

Exploring the Opinion Shifting of Social Media Users Based on Stance Detection

ABSTRACTFine‐grained mining of stance change among social media users during crises contributes significantly to a comprehensive understanding of the development of public opinion online. This study collected detailed information on 227,281 Twitter users who continuously participated in the discussion about the COVID‐19 vaccine to analyze patterns of opinion shifting. Utilizing the COVID‐Twitter‐BERT pre‐trained model, we detect each user's stance on the COVID‐19 vaccine and construct a time‐series dataset reflecting their stance over time. A prediction model for users' opinion shifting is established based on the LightGBM model, and the SHAP explanation method is used to rank the importance of features to identify key features influencing the opinion shifting prediction. Our research findings indicate that nearly half of the users maintained a consistent stance on vaccines, with a relatively low proportion of shifts between pro‐vaccine and anti‐vaccine stances. The F1 value of the prediction model based on the LightGBM model is 0.92. These findings can assist in monitoring social media user opinions online.

Twitter as Knowledge Commons: What Twitter Users Think and Do About Managing Misinformation Issues

ABSTRACTBased on the Governing Knowledge Commons framework, this study examines what users do and think about managing misinformation issues in the Twitter community, and how these are affected by user characteristics. Undergraduates from a public university in the US participated in the study (n = 464) by completing an online survey. Findings shed light on how Twitter community members tackle misinformation issues and inform policies and system designs to support the members' actions and preferences.

Social Media Memory of January 6: Content Analysis of Twitter One Year Later

ABSTRACTWe report on the results of a content analysis of a random sample of tweets (n = 16, 480) about the January 6th insurrection published one year after the attacks. Drawing from research on social media memory, far‐right activism, and social memories in times of crises, we performed a deductive manual coding of the tweets. We found that roughly four of every ten Twitter users remembered the U.S. Capitol attack as an insurrection. Importantly, though, the insurrection frame was adopted by users who were in favor and against the attack. The other most frequent frames were censorship, used by people who aimed to discredit the idea that there had been an insurrection; treason, used by people across the political spectrum to claim that “the other side” had betrayed the United States; fear of other, employed by users who blamed “the others” for the insurrection and its aftermath; and accountability, used by people against the insurrection to call for the attackers to face justice and its leaders to be barred from holding public office. We also noticed that the different frames were not exclusive. Those who used the term “insurrection” frequently used others such as accountability, censorship, treason, terrorism, and conspiracy.

Extraordinarily Time- and Memory-Efficient Large-Scale Canonical Correlation Analysis in Fourier Domain: From Shallow to Deep.

Canonical correlation analysis (CCA) is a correlation analysis technique that is widely used in statistics and the machine-learning community. However, the high complexity involved in the training process lays a heavy burden on the processing units and memory system, making CCA nearly impractical in large-scale data. To overcome this issue, a novel CCA method that tries to carry out analysis on the dataset in the Fourier domain is developed in this article. Appling Fourier transform on the data, we can convert the traditional eigenvector computation of CCA into finding some predefined discriminative Fourier bases that can be learned with only element-wise dot product and sum operations, without complex time-consuming calculations. As the eigenvalues come from the sum of individual sample products, they can be estimated in parallel. Besides, thanks to the data characteristic of pattern repeatability, the eigenvalues can be well estimated with partial samples. Accordingly, a progressive estimate scheme is proposed, in which the eigenvalues are estimated through feeding data batch by batch until the eigenvalues sequence is stable in order. As a result, the proposed method shows its characteristics of extraordinarily fast and memory efficiencies. Furthermore, we extend this idea to the nonlinear kernel and deep models and obtained satisfactory accuracy and extremely fast training time consumption as expected. An extensive discussion on the fast Fourier transform (FFT)-CCA is made in terms of time and memory efficiencies. Experimental results on several large-scale correlation datasets, such as MNIST8M, X-RAY MICROBEAM SPEECH, and Twitter Users Data, demonstrate the superiority of the proposed algorithm over state-of-the-art (SOTA) large-scale CCA methods, as our proposed method achieves almost same accuracy with the training time of our proposed method being 1000 times faster. This makes our proposed models best practice models for dealing with large-scale correlation datasets. The source code is available at https://github.com/Mrxuzhao/FFTCCA.

Tracing views of the intensive mothering discourse in Latvia and on Twitter (X)

ABSTRACT While each new generation since Latvia regained independence has been slowly edging toward libertarianism and equality, childcare in everyday life is still understood as primarily a woman’s burden, echoing both the intensive mothering discourse of Western neoliberal societies and patriarchal traditions inherited from the Soviet gender system. This article aims to map the saturation of ‘intensive parenting’ discourse and differences in opinion between Latvia’s population and Twitter (X) users by comparing the results of a survey involving both samples.

Stroke recovery—what are people talking about on Twitter? A content analysis

Purpose Prioritisation exercises seek out what matters to key stakeholders to inform the planning of research. Social media platforms are potentially useful data sources. The aim was to examine the content of tweets, short messages containing text and pictures, to ascertain the priorities of Twitter users regarding stroke recovery. Materials and methods Content analysis of Twitter was conducted. An electronic search used the identifiers: #strokesurvivor and #strokerecovery. Tweets spanning four weeks from January 2021 were analysed. Results There were 1361 tweets extracted and 486 analysed following exclusion of duplicates and unrelated material. Six themes were uncovered (n = number of tweets): maintaining motivation and positivity (153); sharing of resources (146); raising awareness of stroke (74); symptomatic aspects of recovery (39); experience of rehabilitation (63); and concerns about Covid-19 (17). Conclusions Despite the brevity of tweets, a rich picture arose. A key limitation was lack of biographical data about Twitter users. Recommendations about topics requiring attention from stroke researchers, clinicians and policy makers are: management of psychological problems; public perception of stroke; rehabilitation considerations including treatment burden, person-centred care and equality of care; symptom management including fatigue and aphasia. Findings can be used to supplement and validate other priority-setting exercises.

Individuals’ Motivations and Engagement With Paralympic Content on Social Media: A Longitudinal Analysis Across Six Summer and Winter Games

Despite the recent growth in Paralympic sport programming and viewership on social media, there remains a limited understanding of social media users’ motivations for consuming and engaging with Paralympic content. Drawing on Uses and Gratifications (U&G) theory, the purpose of this study is to examine the motivations of social media users for consuming Paralympic content and the relationship between different types of motivations and social media engagement. Our data collection spanned six Paralympic Games, both Summer and Winter, from 2012 to 2022, resulting in the analysis of 1,297 tweets from unique X (formerly known as Twitter) users. Findings suggest that the prevalent motives for consuming Paralympics content on X include information, integration and interaction, political stance, empowerment, inspiration, and entertainment. Regarding engagement, inspirational content is most likely to be liked, while integration and interaction, and entertainment are more likely to be retweeted.