Usage Of Social Media Platforms Research Articles

Analyzing the Impact of Social Media on College Students' Post Graduation Planning

At present, the popularization rate of higher education has increased, and the world has entered a post epidemic era. The number of graduates has increased year by year, and they are facing the planning problems after graduation, making it more and more difficult to obtain employment. At the same time, social media platforms,i.e.,microblog are booming, and almost all college students have become users of social media platforms, and through these platforms, they can obtain employment and other related information. The purpose of this investigate was to explore the impact of social media information pushed on College Students' post-graduation planning (direct employment). In this paper, "Theory of Planned Behavior" model was applied, and Statistical Product and Service Solutions (SPSS) was applied for confirmatory factor analysis and structural equation modeling. The conclusion of this investigate was that the information pushed of social media platform had an impact on the planning (direct employment) of college students after graduation. The social media platform generated college students to have different attitudes towards employment by influencing their "persistent behavior control". This paper also put forward relevant suggestions on this issue.

Building WOM from Hedonic Experience of Social Media in the Field of Gastronomy

With the popularization of mobile phones and the Internet, users of social media platforms have formed the habit of surfing the Internet. Watching food programs has become one of the most important leisure activities. Food platforms on social media have low barriers to entry, and it is not easy to maintain high popularity, high performance, and high profits. In this context, it is extremely important to continue to gain word-of-mouth from fans. The objective of this study aims at investigating the relationships among hedonic experience, attachment, and word-of-mouth of social media in the field of gastronomy. Data were obtained through interviews and questionnaires. Through the analysis, this paper finds several ways to obtain the word-of-mouth of food programs, namely, hedonic experience - platform attachment - word-of-mouth. This study suggests that platform operators should provide relaxed and pleasant program content and atmosphere to meet users' needs of leisure and learning. For future researchers, future studies can try to add the comparison between utilitarianism and hedonism.

Detecting Arabic Cyberbullying Tweets Using Machine Learning

The advancement of technology has paved the way for a new type of bullying, which often leads to negative stigma in the social setting. Cyberbullying is a cybercrime wherein one individual becomes the target of harassment and hatred. It has recently become more prevalent due to a rise in the usage of social media platforms, and, in some severe situations, it has even led to victims’ suicides. In the literature, several cyberbullying detection methods are proposed, but they are mainly focused on word-based data and user account attributes. Furthermore, most of them are related to the English language. Meanwhile, only a few papers have studied cyberbullying detection in Arabic social media platforms. This paper, therefore, aims to use machine learning in the Arabic language for automatic cyberbullying detection. The proposed mechanism identifies cyberbullying using the Support Vector Machine (SVM) classifier algorithm by using a real dataset obtained from YouTube and Twitter to train and test the classifier. Moreover, we include the Farasa tool to overcome text limitations and improve the detection of bullying attacks.

Social Media Use and Awareness of Privacy Concerns

The usage of social media in our society is prevalent in our daily lives. Although social media usage is at an all time high, the tools and technologies that provide security and protection can be compromised. Users of social media platforms should be made aware of the risks and pitfalls of these applications. Our study identified that users of social media platforms are generally aware of insecurities within the platforms. The researchers determined that the frequency of posting does not cause risks for privacy concerns. Although the users had general awareness and concern, they were heightened after additional information was provided to them in regards to social media security and how personal data is collected and used on social media platforms.

Don’t Be a Victim During a Pandemic! Analysing Security and Privacy Threats in Twitter During COVID-19

There has been a huge spike in the usage of social media platforms during the COVID-19 lockdowns. These lockdown periods have resulted in a set of new cybercrimes, thereby allowing attackers to victimise social media users with a range of threats. This paper performs a large-scale study to investigate the impact of a pandemic and the lockdown periods on the security and privacy of social media users. We analyse 10.6 Million COVID-related tweets from 533 days of data crawling and investigate users’ security and privacy behaviour in three different periods (i.e., before, during, and after the lockdown). Our study shows that users unintentionally share more personal identifiable information when writing about the pandemic situation (e.g., sharing nearby coronavirus testing locations) in their tweets. The privacy risk reaches 100% if a user posts three or more sensitive tweets about the pandemic. We investigate the number of suspicious domains shared on social media during different phases of the pandemic. Our analysis reveals an increase in the number of suspicious domains during the lockdown compared to other lockdown phases. We observe that IT, Search Engines, and Businesses are the top three categories that contain suspicious domains. Our analysis reveals that adversaries’ strategies to instigate malicious activities change with the country’s pandemic situation.

Influence of Social Media Usage on Study Habits of Undergraduates in North Central Nigeria: Implications for Counselling

The study investigated the influence of social media usage on study habits of undergraduates in North Central Nigeria: Implications for counselling. Four objectives and research questions guided the study and four hypotheses were formulated. The study adopted an ex-post facto research design. The population for this study comprises 13,292, 400 level students from four Federal Universities in North Central Nigeria. The sample size for the study was 388 400 level students who were drawn using proportionate stratified and accidental sampling techniques. Two instruments, a structured questionnaire titled “Social Media and Study Habits Questionnaire” (SMSHQ) and a semi-structured interview were used for data collection). The instruments were validated by experts. The reliability of the questionnaire was established using Cronbach Alpha method which yielded a coefficient of 0.71. Data collected for the study were analyzed using Means and Standard Deviation to answer the research questions while Chi-Square Goodness of Fit was used to test the hypotheses at 0.05 level of significance. Findings of the study revealed that, Facebook usage, Twitter usage and Instagram usage have no significant influence on the study habits of undergraduates in North Central Nigeria. WhatsApp usage was however found to significantly influence the study habits of the undergraduates positively. The study concluded that except for WhatsApp platform, the usage of social media platforms like Facebook, Twitter and Instagram negatively affect the study habits of undergraduates in North Central Nigeria. Based on the findings, the researcher recommended that University management in collaboration with counsellors should make strict rules and regulations on the use of smart phones for accessing social media platforms during lecture hours and lecturers should be supported by the management to implement these rules and through counseling, undergraduates should be made to realize all the potential harm from excessive use of social platforms and responsibly approach the learning process.

Hunter Prey Optimization with Hybrid Deep Learning for Fake News Detection on Arabic Corpus

Nowadays, the usage of social media platforms is rapidly increasing, and rumours or false information are also rising, especially among Arab nations. This false information is harmful to society and individuals. Blocking and detecting the spread of fake news in Arabic becomes critical. Several artificial intelligence (AI) methods, including contemporary transformer techniques, BERT, were used to detect fake news. Thus, fake news in Arabic is identified by utilizing AI approaches. This article develops a new hunter-prey optimization with hybrid deep learning-based fake news detection (HPOHDL-FND) model on the Arabic corpus. The HPOHDL-FND technique undergoes extensive data pre-processing steps to transform the input data into a useful format. Besides, the HPOHDL-FND technique utilizes long-term memory with a recurrent neural network (LSTM-RNN) model for fake news detection and classification. Finally, hunter prey optimization (HPO) algorithm is exploited for optimal modification of the hyperparameters related to the LSTM-RNN model. The performance validation of the HPOHDL-FND technique is tested using two Arabic datasets. The outcomes exemplified better performance over the other existing techniques with maximum accuracy of 96.57% and 93.53% on Covid19Fakes and satirical datasets, respectively.

The Relationship between Social Media Usage and Mental Well-Being among Young Adults

Background: The use of social media has grown rapidly over the past decennium and a half, however, not much research is conducted on it to identify its correlation with mental well-being and its effects. Aim: To determine the correlation between social media usage and mental well-being in young adults. Study design: Cross Sectional study. Methodology: Data was collected using convenient sampling. This study includes a sample size of 215 young adults, 108 men, and 107 women, from two universities in Lahore, Pakistan, aged between 18 -25 years. Two instruments were used in this study to measure the variables, the Social Networking Usage questionnaire, and Warwick-Edinburgh Mental Well-being Scale. Data was evaluated by using SPSS version 24. Pearson’s correlation and independent sample t-test were applied with p-value < 0.05 as significant. Results: Findings indicated a significant positive relationship between all dimensions of social media usage including academic, socialization, entertainment, and information. High mean scores indicated that research participants mostly use social media for academic purposes. There was not a statistically significant relationship that could be seen between social media usage and mental well-being. Gender differences were found only related to mental well-being where men scored high as compared to women with a significance of 0.01 level. Practical Implication: Present study results raised the idea of examining other mediating or moderating factors between the connection between social media platforms usage and mental well-being. Not only the time but the content and purpose of social media should also be considered while establishing the direction of the relationship. Conclusion: It was concluded that young adults’ use of social media has not an inverse connection with mental health, and they mostly use it for academic purposes. However, men and women are different on the mental well-being scale, and men with high well-being reported for the present sample. Key words: Social Media, Correlation, Mental Well-Being, Depression and Self-Esteem.

Impact of Social Media Marketing on the Perceptions of E-Shopping Customers in the City of Santo Tomas, Batangas, Philippines

The study investigated the impact of social media marketing on the perceptions of e-shopping customers in the City of Santo Tomas, Batangas, Philippines. Specifically, the study aimed to determine its impact on the perceptions of e-shopping customers as to online visibility, social media engagement, social media integration, social media activities, and social media experience. Moreover, the study also identified the important factors on how social media marketing can be more effective. Lastly, the researchers proposed marketing strategies relative to the findings of the study. The study employed a descriptive-quantitative approach using an adapted questionnaire to gather data from a sample of 150 respondents who were conveniently selected. The statistical tools used in the study were frequency and percentage distribution and weighted mean. The study revealed that the sampled e-shopping customers are active users of social media platforms with Facebook being widely used. They are generally engaged in social media everyday with one-third of them spending three or more hours daily. The study revealed that social media marketing have positively impacted the respondents as e-shopping customers relative to their online visibility, social media engagement, social media integration, social media activities, and social media experience. Moreover, the study found out that brand owners need to focus on the timing and consistency of posts to grow a social media audience. Finally, the study recommended the employment of the proposed marketing strategies which were developed by the researchers based on the findings of the study.

Machine Learning-Based Approach for Fake News Detection

In the modern era where the internet is found everywhere and there is rapid adoption of social media which has led to the spread of information that was never seen within human history before. This is due to the usage of social media platforms where consumers are creating and sharing more information where most of them are misleading with no relevance with reality. Classifying the text article automatically as misinformation is a bit challenging task. This development addresses how automated classification of text articles can be done. We use a machine learning approach for the classification of news articles. Our study involves exploring different textual properties that may be often used to distinguish fake contents from real ones. By using those properties, can train the model with different machine learning algorithms and evaluate their performances. The classifier with the best performance is used to build the classification model which predicts the reliability of the news articles present in the dataset.

Mediatization and patterns of social interaction on social media

There is a correlative relationship between mediatization and social interaction. Communication scholars have paid attention to this relationship. We argue that mediatization involves the incorporation of various patterns of interaction among users of social media platforms. We used two theoretical approaches, namely mediatization and symbolic interaction. We surveyed a purposive sample that we selected according to certain criteria. Regression analysis revealed the correlative relationship between the dimensions of mediatization over social media platforms and the patterns of symbolic interaction among users.

Fight or Flight? Curvilinear Relations between Previous Cyberbullying Victimization Experiences and Continuous Use of Social Media: Social Media Rumination and Distress as Chain Mediators.

Recently, the number of active users of social media platforms is declining, posing a challenge to the sustainability of interest in social media and related industries. Therefore, it is of great significance to examine the environmental and psychological factors that influence the continuous use of social media. Until recently, little research has examined this topic from the perspective of the relationship between previous cyberbullying victimization experiences (PCVE) and the continuous use of social media (CUOSM), not to mention the psychological mechanisms that lead to this relationship. In addition, there are paradoxes in existing studies: one side believes that PCVE causes users to become addicted to using social media, while the other side argues that PCVE drives users to escape from using social media. In order to respond to this controversy and clarify the relationship between PCVE and CUOSM, this study introduces two psychological variables, namely "social media rumination (SMR)" and "distress", in order to construct a chain mediation model. Researchers surveyed 692 people who had experienced social media cyberbullying, and analyzed the data through SPSS and Mplus. The findings were as follows: 1. There is an inverted U-shaped curve relationship between PCVE and CUOSM. Specifically, the relationship initially exhibits a positive correlation (the period named fight), which then becomes negative (the period named flight). 2. When PCVE and CUOSM are positively correlated, SMR is the main factor that contributes to an increase in CUOSM. 3. When PCVE and CUOSM are negatively correlated, distress is the major factor that causes a decline in CUOSM. This study provides an explanation for the controversy in previous research, expands the scope of social media research, and provides a practical reference for social media platforms to enhance their existing users' continuous use.

Usage Of Social Media Platforms To Promote Web Based Library Services

Usage Of Social Media Platforms To Promote Web Based Library Services

Social Media Platforms Usage for Learning and Library Services in Selected Higher Learning Institutions in Zanzibar

This study aimed at examining the usage of social media platforms used on learning and library services in Higher Learning Institutions in Zanzibar. The Study specifically focused on five (5) social media platforms at three selected universities located in Zanzibar. The study involved three research questions. The first question was saying about what are the types of social media platforms used on learning and library services for knowledge sharing in SUZA, ZU, and SUMAIT? The second question said what are the uses of social media platforms used on learning and library services for knowledge sharing in SUZA, ZU, and SUMAIT? And the third question said that what are the challenges facing librarians when social media platforms are used on library services for knowledge sharing in SUZA, ZU, and SUMAIT? The methods that were used in the study include both quantitative and qualitative research designs. Questionnaires and interview tools were used for collecting data to the respondents. The combinations of purposive and stratified random sampling techniques were employed on library users through questionnaires and interviews would take with librarians. The result of this study showed that social media platforms are very well known by the respondents and daily used in their studies. Also, social media are effectively used in most academic libraries to support education progress and most of the respondents prefer using social media in their studies because of Sharing knowledge that involves learning, understanding, extending, and repeating the information, ideas, views, and the resources among persons, connected on a specific ground. The result presented that the availability of social media platforms in the academic library has totally changed the image of the library in terms of delivering the services to the users from the librarians who use social media for reference purposes as a result of having a high number of users on using library through knowledge sharing. The result of the study showed that Poor knowledge of managing and using electronic records and Poor support from the management are the great challenges facing libraries in operating social media platforms on learning and library services for knowledge sharing in higher institutions in Zanzibar as a result of failing to reach many audiences. The study concluded that Social media provide more chances for interaction, connection, sharing, and communication with library users in the library. Librarians could use social media to market their services and resources using different platforms.

Cognitive AI for Mitigation of Misinformation in Online Social Networks

Misinformation propagation in social networks has emerged as a crucial problem that needs to be attended with prime importance. Despite the existence of several fact-checking mechanisms and misinformation detection tools, users of social media platforms continue to be the victims of misinformation propagation. This is because human cognition is a strong factor that drives users in consuming and spreading misinformation. This article highlights the significance of cognitive psychology in misinformation propagation analysis and summarizes the challenges faced by current misinformation detection mechanisms. The study shows that there is an immediate requirement for efficient mechanisms combining AI and cognitive psychology that can support humans in making judgements regarding the information appearing on social networks. A cognitive AI framework is proposed that can augment humans’ capability in assessing the veracity of the information online and reinforce positive information sharing behavior in individuals thereby reducing the spread of misinformation.

Enhanced Seagull Optimization with Natural Language Processing Based Hate Speech Detection and Classification

Hate speech has become a hot research topic in the area of natural language processing (NLP) due to the tremendous increase in the usage of social media platforms like Instagram, Twitter, Facebook, etc. The facelessness and flexibility provided through the Internet have made it easier for people to interact aggressively. Furthermore, the massive quantity of increasing hate speech on social media with heterogeneous sources makes it a challenging task. With this motivation, this study presents an Enhanced Seagull Optimization with Natural Language Processing Based Hate Speech Detection and Classification (ESGONLP-HSC) model. The major intention of the presented ESGONLP-HSC model is to identify and classify the occurrence of hate speech on social media websites. To accomplish this, the presented ESGONLP-HSC model involves data pre-processing at several stages, such as tokenization, vectorization, etc. Additionally, the Glove technique is applied for the feature extraction process. In addition, an attention-based bidirectional long short-term memory (ABLSTM) model is utilized for the classification of social media text into three classes such as neutral, offensive, and hate language. Moreover, the ESGO algorithm is utilized as a hyperparameter optimizer to adjust the hyperparameters related to the ABLSTM model, which shows the novelty of the work. The experimental validation of the ESGONLP-HSC model is carried out, and the results are examined under diverse aspects. The experimentation outcomes reported the promising performance of the ESGONLP-HSC model over recent state of art approaches.

Analysis of Classifiers for Fake News Detection: A Machine Learning Perspective

Abstract: In the present technology, the usage of the net is increasing day by day. Together with the rise in usage of social media platforms like Facebook, Twitter, etc. The news spread among innumerable people within a brief period. Nowadays all and sundry is using social media accounts for communication with one another like within the regions like Political events, Technological area, movie events, etc..... Some people on social media spread the fake news in an immovable way. Nowadays it’s become a troublesome job to detect fake news on social media. Because the platform doesn't verify the activities of users and their posts is difficult to acknowledge that fake news is either a positive thing or a negative thing. As a personality being, it’s tough to detect all this fake news. Solution for this work.

Social stratification and social media disengagement. The effect of economic, cultural and social capital on reasons for non-use of social media platforms

Much of the current research on digital and social media practices uses a Bourdieusian framework to explain stratification processes in the digital realm. This approach typically focusses on social media platform users, neglecting the adequate study of non-users. In this paper, we analyse how cultural, economic and cultural capital are related to reasons non-users in Flanders give for not using social media. We find that access remains a significant obstacle for those with low levels of cultural, economic or social capital, while those with more capital tend to avoid social media over concerns about self-presentation. Education level (as a specific indicator of cultural capital) is also related to both technological skills and technophobia (fear of making mistakes), which are more important barriers for the lower educated. The higher educated also list privacy issues and a lack of time as impediments to social media participation. Implications for research on digital inequalities are discussed in the conclusion section.

Social Media Visual Framing towards Political Participation: An Analysis on BERSIH 2.0

The political atmosphere in Malaysia had witnessed a growing trend of social movement organisations and protests. The recent attention is on the phenomenal record usage of social media platforms as tools to spread political ideology. The multimodal nature of social media has made it an efficient tool where users can post textual information as well as visual materials to reach out to its audience. This article sets out to examine the visual strategy of one of the largest political social movements in Malaysia, the BERSIH movement, within a social media setting. Building on the existing work on visual framing, it asks: How were issues visually portrayed on the BERSIH social media account during the peak of the movement in Malaysia? In this context, Facebook was chosen as the social media platform analysed as it is the main social media used by the movement. Adapting on the level of visual framing, a content analysis was done to a sample of 59 (N=59) top liked photos posted on the Bersih 2.0 Official Facebook account which received more than 0.5% engagement rate (ER= >0.5%). The findings showed that at the denotative level, the main forms of visuals used were photos of protesters, followed by posters and photos of important individuals. The findings also showed that at the connotative level, the main frame highlighted was ‘solidarity’ followed by ‘call for action’ in the form of direct and symbolic visuals. Keywords: Visual framing, framing, social movement, political communication, social media.

How do Fortune firms build a social presence on social media platforms? Insights from multi-modal analytics

The exponential growth in the usage of social media platforms (SMPs) has brought most of us to a virtual space that is nowadays also being shared by firms. Firms regularly communicate over SMPs to elevate consumers' social media experience. With the theoretical underpinning of social presence theory, we have deduced a model that maps multimodal features of Firm-Generated Content (FGC) across three different levels of customer engagement (CE). The model has been empirically tested with Facebook image posts of business-to-consumer companies from the list of Fortune 100 companies of the year 2018. This longitudinal study has also been designed to identify the changes in social media communication due to the pandemic. Our contribution lies in modelling those textual and visual features of FGC that reflect the three different dimensions of social presence. We have used machine learning algorithms to automate the assessment of the experience of social presence. Ultimately, the paper offers social media post design strategies for effective communication and future directions for social media researchers.