Online Social Platforms Research Articles

A REVIEW ARTICLE: USE OF SENTIMENT ANALYSIS IN SOCIAL MEDIA

As a result of the growth of online social networking platforms and applications, a sizeable amount of user-generated text content is created daily in the form of comments, reviews, and short text messages. Users can write messages, share them, and add images and videos to social networking sites like Twitter, Facebook, and others. Consequently, a significant volume of sentiment-rich data is generated. Sentiment analysis then comes into play in this scenario, which evaluates opinions as positive, neutral, or negative by extracting, recognizing, or representing them from various sources, including social media, news, articles, and blogs. This study aims to analyze the results from different sentiment analysis models and technologies that combine natural language processing. Case studies of various industries that can benefit or have been benefiting from sentiment analysis are also discussed to provide an approachable pathway for anyone who wishes to go more deeply into this field. For example, the business world has used it to learn what customers think of a certain company or brand. The impact of profanity on how readers interpret tweets and other social media messages are studied in sociology and psychology. Political scientists are trying to anticipate election results based on tweets to evaluate answers, among other things, and to look for trends, ideological bias, and opinions. Researchers have previously evaluated numerous models using well-known techniques like Naive Bayes, support vector machines, etc., and the findings have been compared with promising outcomes.

Wound care perception and attitude. A school-related experience in Saudi Arabia

Background and Aims: Wound care is a significant global health issue that’s need medical and community attention. The perception of wound care is fundamental among students and teachers in schools to enhance the awareness level and prevents undesired consequences. This study aimed to evaluate students’ and teachers’ level of experience and attitude toward basic knowledge of wound care. Methods: The current study used an electronic survey distributed via online social media platforms among Makkah regions’ schools between January and February 2022. The current study used a convenient sam¬pling method for sampling selection. Then, the recorded data were subjected to statistical analysis. Results: A total of 674 students and teachers from Makkah region were surveyed. The mean (SD) were 22.12 (SD=13.23), female respondents were predominates representing 62.9%. A high level of experience between participants toward wound care were showed in this study 67.06%. A significant association were found between participants’ level of wound care experience and occupational level (P-value, 0.001, 0.024, and 0.012, respectively). Conclusion: Excellent levels of knowledge and attitude towards wound care practice were recorded among most of the participants. However, the awareness of some wound delaying factors and the correct ways to deal with wound injuries, especially for serious cases such as diabetic wounds, is still a challenge for public health awareness.

Analysis of the Challenge in Fake News and Misinformation Regulation Comparative in Global Media Landscape

In the age of online social platforms, increasing interactions beyond the wildest imagination, dealing with fake news has been the most challenging. Perhaps the most visible victims of fake news today are political individuals and institutions. The delicate balance between regulation and respect of individual rights and maintenance of constitutionalism in various countries today creates a unique regulatory dilemma that allows for fake news and the use of it to continue thriving. At the same time, politicians and other institutions occupy a critical role in creating legislation towards combatting fake news. Such moves could significantly undermine the ability to observe some of the fundamental rights of individuals and the overall rule of democracy [1]. Misinformation and other cases of fake news have a relatively significant impact on societies. However, resolving fake news has proved not to be easy because of numerous issues, among them, being the need to preserve fundamental rights [2]. Desktop-based research has been conducted to achieve the objectives of this research. Critical to note that most of the information vital in completing this research is electronically availed. Hence, secondary sources of information have been utilized to reach conclusions on the existence of regulations and its effectiveness toward combating fake news in the three jurisdictions.

老年人在线社交平台功能需求设计研究——基于2018年CHARLS数据

老年人在线社交平台功能需求设计研究——基于2018年CHARLS数据

Dynamic selection of clarification channels in rumor propagation containment.

Rumors refer to spontaneously formed false stories. As rumors have shown severe threats to human society, it is significant to curb rumor propagation. Rumor clarification is an effective countermeasure on controlling rumor propagation. In this process, anti-rumor messages can be published through multiple media channels, including but not limited to online social platforms, TV programs and offline face-to-face campaigns. As the efficiency and cost of releasing anti-rumor information can vary from media channel to media channel, provided that the total budget is limited and fixed, it is valuable to investigate how to periodically select a combination of media channels to publish anti-rumor information so as to maximize the efficiency (i.e., make as many individuals as possible know the anti-rumor information) with the lowest cost. We refer to this issue as the dynamic channel selection (DCS) problem and any solution as a DCS strategy. To address the DCS problem, our contributions are as follows. First, we propose a rumor propagation model to characterize the influences of DCS strategies on curbing rumors. On this basis, we establish a trade-off model to evaluate DCS strategies and reduce the DCS problem to a mathematical optimization model called the DCS model. Second, based on the genetic algorithm framework, we develop a numerical method called the DCS algorithm to solve the DCS model. Third, we perform a series of numerical experiments to verify the performance of the DCS algorithm. Results show that the DCS algorithm can efficiently yield a satisfactory DCS strategy.

Evolution of Public Opinion on COVID-19 Vaccination in Japan: Large-Scale Twitter Data Analysis.

Vaccines are promising tools to control the spread of COVID-19. An effective vaccination campaign requires government policies and community engagement, sharing experiences for social support, and voicing concerns about vaccine safety and efficiency. The increasing use of online social platforms allows us to trace large-scale communication and infer public opinion in real time. This study aimed to identify the main themes in COVID-19 vaccine-related discussions on Twitter in Japan and track how the popularity of the tweeted themes evolved during the vaccination campaign. Furthermore, we aimed to understand the impact of critical social events on the popularity of the themes. We collected more than 100 million vaccine-related tweets written in Japanese and posted by 8 million users (approximately 6.4% of the Japanese population) from January 1 to October 31, 2021. We used Latent Dirichlet Allocation to perform automated topic modeling of tweet text during the vaccination campaign. In addition, we performed an interrupted time series regression analysis to evaluate the impact of 4 critical social events on public opinion. We identified 15 topics grouped into the following 4 themes: (1) personal issue, (2) breaking news, (3) politics, and (4) conspiracy and humor. The evolution of the popularity of themes revealed a shift in public opinion, with initial sharing of attention over personal issues (individual aspect), collecting information from news (knowledge acquisition), and government criticism to focusing on personal issues. Our analysis showed that the Tokyo Olympic Games affected public opinion more than other critical events but not the course of vaccination. Public opinion about politics was significantly affected by various social events, positively shifting attention in the early stages of the vaccination campaign and negatively shifting attention later. This study showed a striking shift in public interest in Japan, with users splitting their attention over various themes early in the vaccination campaign and then focusing only on personal issues, as trust in vaccines and policies increased. An interrupted time series regression analysis showed that the vaccination rollout to the general population (under 65 years) increased the popularity of tweets about practical advice and personal vaccination experience, and the Tokyo Olympic Games disrupted public opinion but not the course of the vaccination campaign. The methodology developed here allowed us to monitor the evolution of public opinion and evaluate the impact of social events on public opinion, using large-scale Twitter data.

Use of Social media by small women entrepreneurs of India for growing their business

With the increasing education level, social awareness, change in attitude and need for more household income have encouraged more and more women to start their own businesses. Online business has been showing a rapid increase in our country in recent times. During the pandemic time, more and more people became aware of the online business platforms. The e- business portals like Amazon, Flipkart, Myntra, Snapdeal, Jabong, etc. became more popular business platforms due to the situation where people preferred to stay inside homes. Swiggy, Zomato, Grofers, Jio Mart, Big basket and others became popular in supplying food staple items during the pandemic time. The increasing presence and growth of such platforms inspired many people to start such online business locally also. Fresh vegetables supply, cooked food services, staple food items and even more items were sold locally through the online platforms. Increasing use of smart phones by women in India made them aware of social media platforms like Facebook, Instagram, WhatsApp, Twitter etc. These platforms have been working as the social networking platforms and are also being used to grow online business by the big businesses as well as by the small local businesses also. My paper is an effort to understand the role of these online social media platforms in the growth of business.

Creating an Online Social Learning Platform: A Model Approach for Open Development, Open Access and Open Education

The importance of online learning platforms in the face of the challenges of the 21st century cannot be stressed enough. Multiple approaches based on different didactic concepts and software have already been discussed. At Karlsruhe Institute of Technology, our team supports the development of an innovative digital infrastructure in creating a virtual campus that provides a portfolio of digital skills and key qualifications for students of all disciplines. The following paper presents this open source-based social online learning platform called hocampus: it aims to function as a model approach for future learning platforms connecting unsupervised learning, peer communication and tutoring as well as teaching. However, our platform is not a mere technical architecture that employs online learning and communication possibilities: it is characterized by a strong correlation of structure and content. For this, we advance a didactic concept focused on empowering students to strengthen their cross-disciplinary key competences and 21st century skills. We also depict the digital infrastructure and tools being used in the creating and operation of hocampus. Lastly, the general design principles for digital platforms are put forward. This paper also presents a firsthand account of how to implement such a learning platform by showing what hindrances need to be overcome, how students benefit from a social online learning platform and how digital learning can develop and change in the coming years. Thus, it can function as a manual portraying the necessary steps for the realization of concrete didactic concepts in a digital space.

Community-oriented Motivational Interviewing (MI): A novel framework extending MI to address COVID-19 vaccine misinformation in online social media platforms

Researchers have linked circulating misinformation in online platforms to low COVID-19 vaccine uptake. Two disparate literatures provide relevant initial guidance to address the problem. Motivational Interviewing (MI) effectively reduces vaccine hesitancy in clinical environments; meanwhile, social scientists note inoculation, rebuttal, and appeals to accuracy are persuasive in digital contexts. A tension is inherent in these approaches. MI in digital forums may induce an ‘illusory truth effect,’ wherein falsehoods appear more accurate through repetition. Yet, rebutting misinformation directly may elicit backfire or reactance effects, motivating some to amplify their presentation of misinformation. Building on Identity Process Theory, we propose a theoretical framework for conducting MI-based infodemiology interventions among digital communities that conceptualizes the community in toto (rather than one specific person) as the unit of focus. Case examples from interventions on public Facebook posts illustrate three processes unique to such interventions: 1) Navigating tension between addressing commenters and “bystanders”; 2) Activating pro-vaccine bystanders; and 3) Reframing uncertainty or information individuals might find concerning or threatening according to implied collective values. This paper suggests community-oriented MI can maximize persuasive effects on bystanders while minimizing potential reactance from those with committed beliefs, thereby guiding community-oriented public health messaging interventions enacted in digital environments.

The Use of Online Social Media Platforms by Tanzania Journalists to Produce and Disseminate Development News

Advancement in Information and Communication Technologies (ICT) are revolutionizing Development Journalism (DJ) into an effective strategy for building competitive economies globally. However, many countries in Africa including Tanzania are slow in tapping potentials of ICT for development journalism. Digital penetration in the form of the Internet and social media are changing the way in which journalists are mobilizing and engaging communities in journalism practises, a key strategy for a competitive digitalised economy. This paper was guided by Development Communication Theory and Diffusion of Innovation Theory to explore the use of online social media by journalists in Tanzania to practice development journalism. Combining quantitative and qualitative methods, this paper analyses risks and benefits of online social media platforms in contributing to national development goals. A total of 15 social media journalists and managers from Mwananchi Digital, Ayo TV and Azam TV gave their insights in this paper. Use of online social media platforms for development news is still in its infancy stage, key findings show that out of 270 (100%) studied news items, only 66 (24%) manifested development news practice. Non-development news accounted for 204 (76%) of news items analysed. There were only four (4) (27%) journalists who use social media as a source of information, and platform for disseminating development news in Ayo TV compared to 3 (20%) in Mwananchi Digital and 5 (33%) in Azam TV. Results call upon some intensive national efforts to empower journalists in the use of ICT and mobilize audience in the changing communication patterns.

Hierarchical attention neural network for information cascade prediction

Online social networking platforms have drastically facilitated the phenomenon of information cascades, making cascade prediction an important task for both researchers and practitioners. In cascade propagation paths, influential users can often attract more attention. Moreover, the community structure formed by users with similar interests creates information redundancy, thereby restricting the propagation process. These two features greatly affect the growth of the cascades. This paper investigates the incremental prediction of cascades during a future time period based on the evolution of cascades in early stages and proposes a neural network framework with hierarchical attention mechanisms, named Hierarchical Attention Cascade Neural Network (CasHAN). This network has a node-level attention mechanism based on user influence and a sequence-level attention mechanism based on community redundancy. User influence considers the user’s own attributes and the influence feedback provided by neighbors, while community redundancy measures information redundancy characteristics that limit cascade propagation. Through hierarchical attention mechanisms, the effective combination of these two features improves the accuracy of cascade increment prediction. Extensive experiments on real-world datasets demonstrate that our approach outperforms other state-of-the-art prediction methods.

Lessons Learned From an Effectiveness Evaluation of Inlife, a Web-Based Social Support Intervention for Caregivers of People With Dementia: Randomized Controlled Trial.

Informal care for people with dementia not only affects the well-being of the primary caregiver but also changes their roles and interactions with the social environment. New online interventions might facilitate access to social support. Recently, an online social support platform, Inlife, was developed in the Netherlands and aims to enhance social support and positive interactions in informal support networks. This study aimed to evaluate the effectiveness of Inlife for caregivers of people with dementia. A randomized controlled trial with 96 caregivers of people with dementia was performed. Participants were randomly assigned to the Inlife intervention or the waiting list control group. After 16 weeks of Inlife use, the waiting list control group could start using Inlife. Effects were evaluated at baseline (T0), 8 weeks (T1), and 16 weeks (T2). The 16-week follow-up assessment (T2) served as the primary endpoint to evaluate the results for the primary and secondary outcome variables evaluated with online self-report questionnaires. The primary outcomes included feelings of caregiver competence and perceived social support. The secondary outcomes included received support, feelings of loneliness, psychological complaints (eg, anxiety, stress), and quality of life. No significant improvements were demonstrated for the intervention group (n=48) relative to the control group (n=48) for the primary outcomes (feeling of carer competence: b=-0.057, 95% CI -0.715 to 0.602, P=.87; perceived social support: b=-15.877, 95% CI -78.284 to 46.530, P=.62) or any secondary outcome. This contrasts with our qualitative findings showing the potential of Inlife to facilitate the care process in daily life. Adherence was not optimal for all Inlife users. Additional per-protocol and sensitivity analyses also revealed no beneficial results for high active Inlife users or specific subgroups. Inlife users were more active when part of a larger network. Researchers should be modest regarding the effectiveness of online caregiver interventions in terms of quantitative measures of well-being and quality of life. Nevertheless, online tools have the potential to facilitate the caregiver process in daily life. Lessons learned include the importance of harnessing the power of human interaction in eHealth, making use of the user's social capital, and the need to develop research methods that can identify benefits in daily life that are ecologically valid for caregivers. Netherlands Trial Register NTR6131; https://trialsearch.who.int/Trial2.aspx?TrialID=NTR6131. RR2-10.1186/s13063-017-2097-y.

A Transformer Based Approach for Abuse Detection in Code Mixed Indic Languages.

The advancement in the number of online social media platforms has entailed active participation from the web users globally. This has also lead to subsequent increase in the cyberbullying cases online. Such incidents diminish an individual’s reputation or defame a community, also posing a threat to the privacy of users in cyberspace. Traditionally, manual checks and handling mechanisms have been used to deal with such textual content. However, an automatic computer-based approach would provide far better solutions to this problem. Existing approaches to automate this task majorly involves classical machine learning models which tend to perform poorly on low resource languages. Owing to the varied background and language of web users, the cyberspace witnesses the presence of multilingual text. An integrated approach to accommodate multilingual text could be the appropriate solution. This paper explores various methods to detect abusive content in 13 Indic code-mixed languages. Firstly, baseline classical machine learning models are compared with Transformer based architecture. Secondly, the paper presents the experimental analysis of four state-of-the-art transformer-based models vis à vis XLM-RoBERTa, indic-BERT, MurilBert and mBERT, out of which XLM Roberta with BiGRU outperforms. Thirdly, the experimental setup of the best performing model XLM-RoBERTa is fed with emoji embeddings that leads to further enhancement of overall performance of the employed model. Finally, the model is trained with the combined dataset of 13 Indic languages, to compare its performance with those of individual language models. The performance of combined model surpassed those of the individual models in terms of F1 score and accuracy, supporting the fact that combined model fits the data better possibly due to its code-mixed nature. This model reports a F1 score of 0.88 on test data while rendering a training loss of 0.28, validation loss of 0.31 and an AUC score of 0.94 for both training and validation.

Classifying the Evolving Mask Debate: A Transferable Machine Learning Framework

Anti-maskers represent a community of people that opposes the use of face masks on grounds that they infringe personal freedoms. This community has thoroughly exploited the convenience and reach of online social media platforms such as Facebook and Twitter to spread discordant information about the ineffectiveness and harm caused by masks in order to persuade people to shun their use. Automatic detection and demoting of anti-mask tweets is thus necessary to limit their damage. This is challenging because the mask dialogue continuously evolves with creative arguments that embed emerging knowledge about the virus, changing socio-political landscape, and present policies of public health officers and organizations. Therefore, this paper builds a transferrable machine learning framework that can separate between anti-mask and pro-mask tweets from longitudinal data collected at four epochs during the pandemic. The framework extracts content, emotional, and engagement features that faithfully capture the patterns that are relevant to anti-mask rhetoric, but ignores those related to contextual details. It trains two ensemble learners and two neural network architectures using these features. Ensemble classifiers can identify anti-mask tweets with approximately 80% accuracy and F1-score from both individual and combined data sets. The invariant linguistic features extracted by the framework can thus form the basis of automated classifiers that can efficiently separate other types of falsehoods and misinformation from huge volumes of social media data.

Enhancing Detection of Arabic Social Spam Using Data Augmentation and Machine Learning

In recent years, people have tended to use online social platforms, such as Twitter and Facebook, to communicate with families and friends, read the latest news, and discuss social issues. As a result, spam content can easily spread across them. Spam detection is considered one of the important tasks in text analysis. Previous spam detection research focused on English content, with less attention to other languages, such as Arabic, where labeled data are often hard to obtain. In this paper, an integrated framework for Twitter spam detection is proposed to overcome this problem. This framework integrates data augmentation, natural language processing, and supervised machine learning algorithms to overcome the problems of detection of Arabic spam on the Twitter platform. The word embedding technique is employed to augment the data using pre-trained word embedding vectors. Different machine learning techniques were applied, such as SVM, Naive Bayes, and Logistic Regression for spam detection. To prove the effectiveness of this model, a real-life data set for Arabic tweets have been collected and labeled. The results show that an overall improvement in the use of data augmentation increased the macro F1 score from 58% to 89%, with an overall accuracy of 92%, which outperform the current state of the art.

A cross-sectional survey of German PA employment and workforce entry.

The contribution of physician assistants (PAs) to the German healthcare workforce has increased significantly since their introduction in 2005. From five training programs, the number has increased to the current 18, with 560 PAs awarded the PA bachelor of science degree as of 2020. Despite the growth, researchers lack systemic and reliable empirical data that provide insight into the German PA educational and professional profile. The German University Association Physician Assistant (DHPA) undertook the first nationwide cross-sectional survey on PAs in Germany to understand the German PA movement. This survey aimed to describe German PAs' entry into the profession and PA educational and job satisfaction. PA alumni of all universities affiliated with the DHPA and all subscribers of the Facebook online social media platform PA Blog were invited to complete an online questionnaire. Of the 282 PAs who completed the survey, 77% were female and under age 25 years. Almost all (94%) were employed, predominantly as PAs (91%, 241 of 265), although some held other positions. Most worked full time (87%), with some citing child-care needs as reasons for part-time employment (n = 21). Few reported unemployment (1.4%, 4 of 282). Eighty-two percent said they would probably or very likely choose the same course of study again. Most employed participants found the inclusion of frequent rotations between didactic and clinical training in PA programs beneficial. However, a small number of participants (26.8%) agreed that German PA programs' didactic and clinical teaching objectives were well aligned. German PAs have a high level of satisfaction with their profession and report low unemployment. Improvement in the alignment of didactic and clinical educational objectives to improve academic qualifications and satisfaction emerged as an area of research.

The positive energy of netizens: development and application of fine-grained sentiment lexicon and emotional intensity model.

The outbreak of COVID-19 has led to a global health crisis and caused huge emotional swings. However, the positive emotional expressions, like self-confidence, optimism, and praise, that appear in Chinese social networks are rarely explored by researchers. This study aims to analyze the characteristics of netizens' positive energy expressions and the impact of node events on public emotional expression during the COVID-19 pandemic. First, a total of 6,525,249 Chinese texts posted by Sina Weibo users were randomly selected through textual data cleaning and word segmentation for corpus construction. A fine-grained sentiment lexicon that contained POSITIVE ENERGY was built using Word2Vec technology; this lexicon was later used to conduct sentiment category analysis on original posts. Next, through manual labeling and multi-classification machine learning model construction, four mainstream machine learning algorithms were selected to train the emotional intensity model. Finally, the lexicon and optimized emotional intensity model were used to analyze the emotional expressions of Chinese netizens. The results show that POSITIVE ENERGY expression accounted for 40.97% during the COVID-19 pandemic. Over the course of time, POSITIVE ENERGY emotions were displayed at the highest levels and SURPRISES the lowest. The analysis results of the node events showed after the outbreak was confirmed officially, the expressions of POSITIVE ENERGY and FEAR increased simultaneously. After the initial victory in pandemic prevention and control, the expression of POSITIVE ENERGY and SAD reached a peak, while the increase of SAD was the most prominent. The fine-grained sentiment lexicon, which includes a POSITIVE ENERGY category, demonstrated reliable algorithm performance and can be used for sentiment classification of Chinese Internet context. We also found many POSITIVE ENERGY expressions in Chinese online social platforms which are proven to be significantly affected by nod events of different nature.

SURVEY: YOUTUBE SPAM COMMENTS DETECTION AND DELETION

The quality of online social platforms has risen, and spammers have developed a number of strategies to trick consumers into clicking on harmful links. This is accomplished by posting spam to various social media networks' comment sections. This paper suggests a method for identifying spam comments on YouTube, which have grown significantly recently. YouTube operates a spam blocking system, although it consistently fails to do so effectively so our program tries to tackle the problem by not only detecting but also deleting the spam comments by using Machine Learning

Sentiment analysis using lexico-semantic features

Sentiment analysis of the text deals with the mining of the opinions of people from their written communication. With the increasing usage of online social media platforms for user interactions, abundant opinionated textual data emerges. Therefore, it leads to increased mining of opinions and sentiments and hence greater interest in sentiment analysis. The article introduces the novel Lexico-Semantic features and their use in the sentiment polarity task of English language text. These features are derived using the semantic extension of the lexicons by employing sentiment lexicons and semantic models. These features make data sample size consistent when used in deep learning settings, thereby eliminating the zero padding. For evaluation, we use different semantic models and lexicons to determine the role and impact of Lexico-Semantic features in classification performance. These features, along with the other features, are used to train the different classifiers. Our experimental evaluation shows that introducing Lexico-Semantic features to various state-of-the-art methods of both machine and deep learning improves the overall performance of classifiers.

Multi-stage Transfer Learning for Fake News Detection Using AWD-LSTM Network

In the recent decades, the automatic veracity verification of rumors is essential, since online social media platforms allow users to post news item or express opinion towards a circulating piece of information without much restriction. The intention of fake news is to make the readers believe in inaccurate information, where the detection of fake news by using content is a difficult task. So, the auxiliary information: user profile, social engagement of the users, and other user’s comments are useful in the detection of fake news. In this manuscript, a novel multi-stage transfer learning approach is introduced for an effective fake news detection, where it utilizes user’s comments as auxiliary information to detect whether the given tweet is true or false. The stances of the response tweets contain opinions on news/rumors are often used for verifying the veracity of the circulating information. In order to devastate the effects of the specific rumors at the earliest, the multi-stage transfer learning approach automatically predict veracity of rumors jointly with the stances of their response tweets. The proposed multi-stage transfer learning is an inductive transfer learning variation that is used to forecast the stance of responses, then to identify fake news. The proposed model’s effectiveness is evaluated on the two-benchmark datasets: semEval-2017 task 8 and PHEME. The proposed model outperformed the existing approaches by obtaining a classification accuracy of 64.30% and 65.30%, an F-measure of 65.95% and 63.90% on semEval-2017 task 8, and PHEME on event-wise datasets.