Today's Social Media Research Articles

Deep Pattern Analysis for Cyberbullying Detection using Probabilistic Analytical Learning

Abstract: Cyberbullying has emerged as a significant issue in today's social media landscape, posing various detrimental effects. The combination of photo sharing and text comments has exacerbated the severity of cyberbullying incidents. Automated detection tools are crucial for ensuring the health and security of these platforms. However, traditional approaches that analyze text and images separately may fail toidentify all instances of cyberbullying, especially whenseemingly innocent content conveys bullying messages when posted together. This research proposes a novel system that extracts combined features from text and images to identify diverse cases of cyberbullying. The system can extract profiles based on behavior and uncover latent ties between users and groups with similar behaviors. Our approach utilizes methods log mining, business analysis, complex networks, and graph theory to achieve this. This paper outlines the entire process, from log file analysis to the construction of the user graph, witha particular focus on the step known as The finding of user behavioral patterns.

Effects of Social Media Platform on Generation Z in Personality Development

Today's Social media platforms have become an integral part of Generation Z's lives, profoundly shaping their personality development. Teenagers born between 1996 and 2010 are very closely related to technology. Every year the number of people using at least one social platform increases. This study explores the multifaceted influence of social media, highlighting both its potential to empower self-expression, community building, and social awareness, and its capacity to fuel comparison, anxiety, and an unhealthy dependence on external validation. Critical characteristics of friendships, including validation, self-disclosure, and companionship, and instrumental support, can occur in equally effective and satisfying ways offline and online. By understanding these contrasting effects, we can encourage Gen Z to leverage the positive aspects of social media for self-discovery and connection while mitigating the potential for negative impacts on their developing personalities. The effects of social media platforms on Generation Z in personality development which is confirmed by p-values for six opinions by the Chi-Square test, are 0.0233, 0.024, 0.026, 0.01656, 0.007, and 1.05E04. For statistical Analysis, I used ORIGIN 2019 software. Research gaps in social media's influence on Gen Z's personality suggest the need for longitudinal studies to track long-term effects, exploration of platform-specific impacts, identification of mitigating strategies, understanding neurological implications, and consideration of global vs. regional differences. Addressing these gaps can inform interventions for healthy online behavior. Keywords: Generation Z, social media, personality development,

Analisis Penjualan Berdasarkan Pengembangan Konten Media Sosial: Studi UMK Atmosphere Beauty Kota Bukittinggi Pada Media Tiktokshop dan Shopee Tahun 2023

In today's social media era, various groups utilize social media for various purposes because it has many benefits. In everyday life, social media is useful as a socialization tool, a source of information, a source of entertainment, a place to channel hobbies, even as an online business platform and promotion. This study aims to measure the sales growth of Atmosphere Beauty products, an MSME in Bukit Tinggi City, West Sumatra, based on content posted on Atmosphere Beauty's TikTok social media. The research method used is a qualitative method by collecting primary and secondary data through interviews, documentation, and observation. In this study, the authors managed to find that the content produced on the TikTok @atmosphere.beauty account refers to three of the four aspects of marketing content, namely education, inspiration, and conversion. The results show that although sales at TikTok Shop are on the rise, Atmosphere Beauty's MSE sales are less than optimal because their TikTok account is less active. The account is only active on Instagram, where they directly include Shopee links for product sales, so Atmosphere Beauty's followers directly access Shopee without going through TikTok Shop.

Rumor Source Detection in Subgraphs: An ML Approach

Social networking sites offer a vast platform for sharing various types of content, such as information, photos, videos, and audio clips. However, the credibility of the information shared on these sites is a significant concern since there is no prior verification process as the information spreads across the networks. This increases the chances of disseminating false or misleading information, often called rumors. The spread of rumors in today's information environment creates severe problems for the credibility of information and public confidence. The quick spread of rumors, frequently conveyed via social media and other online platforms, can affect public opinion and potentially have real-world repercussions. Maintaining the integrity of information ecosystems and averting the potentially damaging impacts of disinformation require detecting and mitigating rumors. In today's social media and online communication age, it is crucial to identify rumors to prevent their spread and mitigate their potential negative impact. In this study, our primary goal is to discover and identify individual sources of rumors. This work addresses two aspects of rumor management: firstly, identifying the difference between rumors and facts, and secondly, tracking the source of the rumor. In conjunction with the attributes, state-of-the-art methods such as SVM, AdaBoost, Random Forest, Logistic Regression, and Graph Convolutional Networks (GCN) are used to accomplish these goals. This approach contributes to the broader goal of combating disinformation and preserving the Accuracy of information.

Audit Komunikasi Strategi Digital Universitas Muhammadiyah Kotabumi dalam Menguatkan Brand Image di Instagram

The fast-growing technology on social media has changed the behavior of the public in receiving information. Today's social media use in Indonesia is growing so rapidly every year. According to Melansir Data Reportal, by 2023, there are 167 million social media users out of 153 million over the age of 18, which is 79.5% of the total population. The purpose of this research is to analyze the effectiveness of digital branding and positioning strategies carried out by the University of Muhammadiyah Kotabumi with the approach of auditing communication using the method of SOSTAC. The results of this study show that the University has not yet had a field of human rights, so UMKO's identity is not maximum, branding, and postitoning are not well managed and the use of social media especially Instagram is not maximal even can be passively regulated.

The Loop and Reasons to Break It: Investigating Infinite Scrolling Behaviour in Social Media Applications and Reasons to Stop

Today's social media (SM) platforms are toolkits consisting of features with different use cases, some strongly related to habitual and regretful use. Especially Infinite Scrolling (IS) has been reported to make users feel like they are being caught in a loop, regretfully elongating SM sessions. We investigated and defined this loop while unveiling the processes that make users break it. Based on a one-week-long field study (N=46), we unfolded and categorized general reasons for leaving social media and related those to IS. In light of our findings, we argue that SM interventions should not only focus on the app but incorporate the user's context, as most reasons to break SM sessions were not related to the app but the user's general context. Our findings and prior work also indicate the coexistence of multiple loops, which we define as inner (intra-session) loops surrounded by an outer (habitual) loop.

Sinergisitas Humas dan Jurnalistik sebagai Media Informasi pada Pemerintahan Provinsi Sumatera Utara : Studi Kasus Akun Instagram @Infosumutku

Today's social media, which consists of various platforms, has become the daily food for people from all walks of life. Parents, youth and children all have free access to social media. All circulating information can be reached with just one touch on smartphones and other electronic devices. Technological developments play a major role in the development of human civilization, especially in North Sumatra. Information that is educational to entertainment is very important to be accepted by the community. Since 2019 the Provincial Government of North Sumatra has no longer assigned the Public Relations Bureau to carry out public relations tasks, but has been assigned to the North Sumatra Communication and Information Service (Kominfo).Pemprovsu views social media Instagram @infosumutku as media that is very close to the community. In addition to the existence of this platform which is widely used by the public, Pemrovsu not only uses Instagram as a medium of information for the public, but also Twitter, Facebook, Tiktok, and the Website. North Sumatra Kominfo as an executor in the field of public relations at Pemprovsu has a strategy in carrying out its duties of disseminating information to the public. Not only that, North Sumatra Kominfo has many relationships with journalists and mainstream media which of course are embraced to become partners in disseminating information to meet the needs of the people of North Sumatra in particular.
 Keywords: Synergy, Public Relations, Journalism, Information Media

Pengaruh Sosial Media Dikalangan Anak dan Remaja

In today's modern era, all influences in the world have begun to change. Currently the biggest influence is the presence of social media for children and adolescents. Social media currently has a major influence on society, changing the paradigm without knowing the boundaries of space, time, distance, anytime, anywhere, and without direct communication or meeting someone face to face. Through social media, of course, it will be easier to communicate in every community. Social media also brings many new events that have an impact on the development of our lives, especially on the growth and development of children and adolescents, from negative and positive consequences. Most social media users are children and adolescents who still need monitoring in their use. However, today's social media also has positive and negative influences for children and adolescents. In addition, social media also has a pretty good impact on the community. In fact, even at a young age, you can already use social media or something like that.

A Semiotic Analysis on FIFA World Cup 2022 Qatar Memes

Memes have become a unique way of conveying messages and sharing experiences in today's social media era. The FIFA World Cup is one of the biggest sporting tournaments in the world, and its audience, which is divided into various regions and circles, has attracted researchers to make it an object. The aims of this semiotic analysis study are to determine the signifier and the signified, as well as the denotation and connotation, as well as the meaning of FIFA World Cup Qatar 2022 memes. The descriptive qualitative method is being used in the study. To analyze the data, the researchers applied Roland Barthes' theory. Memes are classified as signifiers and signified, which can be expressed verbally or visually. The researchers also explained the denotative and connotative interpretations of the 2022 FIFA World Cup in Qatar. The writers selected four memes for this analysis that talked about watching experiences, trolling the fans and players, and giving thoughts about the FIFA World Cup 2022 Qatar tournament. The results show that the signifiers in the memes were very random and unique, such as the heartbeat display in the first image, scientists in the second image, actors in the third image, scientists, and cartoon characters with flags in the last image. These signs certainly have objective or literal meanings (denotation) and subjective or other meanings (connotation). Most of the connotational meaning from memes that have been analyzed focuses on sharing the experience of watching the FIFA World Cup 2022 competition and also trolling the football supporters or even the players that participated

Penyebaran Berita Politik dan Partisipasi Politik Masyarakat Kota Palu di Media Sosial

Today's social media has created a new dilemma. Media independency is an important component for a democratic order, however, in some contexts, citizens experience several hindrance to fully enjoy this right. Replacing conventional media channels, social media is becoming an indispensable medium for expressing and discussing politics. This research focuses on the political participation of the people of Palu City which is influenced by the presence of social media. The social media means are Facebook, WhatsApp, Instagram, Twitter, TikTok, YouTube, and Telegram. This study was designed using a quantitative approach. The techniques used to collect the data include observation, questionnaires, and written documents. This research questionnaire was distributed to the people of Palu City which was carried out directly and through social media. The results of distributing the questionnaires showed that 144 respondents were willing to fill out the questionnaires. Data analysis in this study used descriptive statistics. The results of the study show that the political participation of the people in Palu City places more emphasis on spreading news or political issues on social media, especially by spreading the news or issues on sundury social media accounts, but not only that, the political participation of the people is also shown by receiving and following the news. -News and political issues on social media. The political news or issues shared on social media in this study was carried out by the public if they received news or political issues that were hotly discussed. News or issues that are disseminated are no longer managed, but are immediately distributed on various social media accounts such as Facebook, WhatsApp, Instagram, Twitter, TikTok, YouTube, and Telegram, so it is not uncommon for news or issues to have a positive impact, it some even have an negative impact.

Psychological Impact of social media on Rural Youth: A Study

Today social media has created a stir in the world, but social media has been born with the advent of the internet, if there was no internet today, then hardly nowadays is the magic of social media speaking in the heads of youth especially and its effect is also affecting more youth. Today's youth have become crazy about social media and they cannot live without it. The Internet is the heartbeat of social media. The beat of youth also stops when they walk in the internet social media would have originated, the role of the internet is important in advancing the media. In today's time, social media is psychologically affecting the youth.

Mutual-Enhanced Incongruity Learning Network for Multi-Modal Sarcasm Detection

Sarcasm is a sophisticated linguistic phenomenon that is prevalent on today's social media platforms. Multi-modal sarcasm detection aims to identify whether a given sample with multi-modal information (i.e., text and image) is sarcastic. This task's key lies in capturing both inter- and intra-modal incongruities within the same context. Although existing methods have achieved compelling success, they are disturbed by irrelevant information extracted from the whole image and text, or overlooking some important information due to the incomplete input. To address these limitations, we propose a Mutual-enhanced Incongruity Learning Network for multi-modal sarcasm detection, named MILNet. In particular, we design a local semantic-guided incongruity learning module and a global incongruity learning module. Moreover, we introduce a mutual enhancement module to take advantage of the underlying consistency between the two modules to boost the performance. Extensive experiments on a widely-used dataset demonstrate the superiority of our model over cutting-edge methods.

On The Influence of Modern New Social Media on Brand Effect

The rapid development of the Internet and new social media also happened quickly. In a short period, new media has grown from nothingness to a powerful position. Today's social media is no longer a simple communication platform. However, there are many trends. Social media is a favorite of many brands in a business environment and functions as a marketing channel. Social media has a significant impact on brands in this new relationship. In the ever-changing new media landscape, brands need a piece of the pie. This article takes how to enhance brand influence in the new media era as the research object. By analyzing the characteristics of new media, we get the possibility of enhancing brand influence. At the same time, we fully recognize the principle of enhancing brand influence in new media. By putting forward directional opinions, we strive to maximize the promotion of brand influence

Corporate training for developing social media literacy skills: personalized approach

Today social media can be a highly effective tool in business by attracting new customers, getting their feedback, building loyalty, and increasing a company's market reach. However, what happens when it goes wrong? One of the most common problems with social media is that information that was previously private can now be presented to the world by one mouse click. Employees are directly linked to their employers on social media, so if an employee writes a controversial statement online, reputational damage to a company can be devastating. Hence, employees should receive basic social media literacy, to have the proficiency to communicate appropriately and responsibly. The only providers of this educational content for learning and development (LD) divisions are established media outlets that could force positive changes to the way companies learn. Upskilling and reskilling of employees have become a significant objective in strategic development for many companies, according to LinkedIn research. One-size-fit-for-all training approach is no longer effective. Therefore, even the development of social media literacy skills should be personalized. The study aims to determine: 1) contemporary understanding of media literacy skill in business context; 2) characteristics of the personalized learning (PL) environment that impact on learning outcomes; 3) personalized learning tools. Theoretical analysis is used to identify contemporary empirical studies associated with the implementation of PL in corporate learning between 2018 and 2022.

Deep Learning for Depression Detection Using Twitter Data

Today social media became a communication line among people to share their happiness, sadness, and anger with their end-users. It is necessary to know people’s emotions are very important to identify depressed people from their messages. Early depression detection helps to save people’s lives and other dangerous mental diseases. There are many intelligent algorithms for predicting depression with high accuracy, but they lack the definition of such cases. Several machine learning methods help to identify depressed people. But the accuracy of existing methods was not satisfactory. To overcome this issue, the deep learning method is used in the proposed method for depression detection. In this paper, a novel Deep Learning Multi-Aspect Depression Detection with Hierarchical Attention Network (MDHAN) is used for classifying the depression data. Initially, the Twitter data was preprocessed by tokenization, punctuation mark removal, stop word removal, stemming, and lemmatization. The Adaptive Particle and grey Wolf optimization methods are used for feature selection. The MDHAN classifies the Twitter data and predicts the depressed and non-depressed users. Finally, the proposed method is compared with existing methods such as Convolutional Neural Network (CNN), Support Vector Machine (SVM), Minimum Description Length (MDL), and MDHAN. The suggested MDH-PWO architecture gains 99.86% accuracy, more significant than frequency-based deep learning models, with a lower false-positive rate. The experimental result shows that the proposed method achieves better accuracy, precision, recall, and F1-measure. It also minimizes the execution time.

How can context and information content of advertising increase sales of advertising products on social media?

This paper aims to understand how the information presented on social media can move the roads and business partners today. The author believes that the more attractive the content and where an advertisement is on social media, the more business sales will increase sales. As a result of a good review and high reliability. After a series of reviews and discussions of the results, advertising content information on various social media platforms has been proven to increase business sales results. This happens because today's social media is a place for friendship and teaching for the promotion and advertising of various business products and services. It is hoped that these findings will become a scientific repertoire of similar study approaches in the future.

Meme Detection of Journalists from Social Media by Using Data Mining Techniques

With regard to today's social media networks, memes have become central. Share a million memes per second on different social media. The detection of memes is a very concentrated and demanding subject in the current field of research. Share about a million memes on various social media. Today's social media (What's App, Twitter, and Facebook) is widespread around the world. Since people in all countries are heavily used, use a set of social media application data (Twitter). As social media has an enormous amount of data overall the world. That will use that data set of Twitter for meme detection of journalists in Pakistan. So, this is done by getting data set from social media (Twitter, What’s App, and Facebook) by using their authenticated APIs. For this analysis use some opinion mining techniques and sentiment analysis like the statistical descriptive and content analysis. In our society, it is the better way to analysis about any journalists because social media can provide very huge amounts of data about any journalist which is true or false but I can make approximate correct perceptions by using sentiment analysis and text mining techniques. It will provide highly wanted and hidden characteristics and perceptions for searchers and demanding people about journalists. Finally use for sentiment analysis by using Python.

STUDI INTEGRATIF TEOLOGI DAN MEDIA SOSIAL

Today's technological developments have provided very easy access for the current generation or so-called generation Z to be able to get the information they need. However, the problem occurs when Generation Z misreads information, one of which is information related to the doctrines of the Christian faith. Therefore, it is necessary to formulate correct theological thinking with the development of today's social media. Through qualitative methods with an integrative study approach between theology and social media and phenomenological studies related to the problems that arise. So this research produces a combination of theology and social media that contributes in terms of social media content filled with true theology and theology that is open in general because it is bridged by social media. This research contributes so that Generation Z is not trapped in wrong doctrines in social media.

Utilization of Facebook Live Streaming in Online Missionary Endeavor at the Ar-Risalah Al-Khairiyah Foundation

Today's social media is experiencing a very big development. Many social media platforms are competing to present the latest features to attract the interest of netizens or users. One of the large and widely used social media platforms in Indonesia is Facebook. Since 2015, Facebook has officially added live streaming features to its applications, both for Android, iOS and PC applications. The emergence of the Facebook live streaming feature is in great demand by content creators, gamers, academics and also preachers both individually and in institutions. The Arrisalah Alkhairiyah Foundation is a social, educational and da'wah foundation that has a da'wah office that oversees the Isyraf Dakwi division. Various da'wah programs carried out by the Isyraf Dakwi division, one of which is conducting a live streaming study using social media Facebook. This study uses a qualitative descriptive method, the purpose of which is to describe the use of Facebook live streaming social media for online da'wah activities. The research findings, it was found that the use of Facebook live streaming was initially an alternative da'wah program which was stopped due to the covid 19 pandemic. The advantages of the program through this live streaming are that it is cost and time efficient and is easily accessible to viewers and the study materials are kept stored. The obstacles encountered in live streaming are the poor internet connection and the lack of promotion of Isyraf Dakwi's account channel so that the number of viewers tends to tend to

Fine-Tuning BERT Based Approach for Multi-Class Sentiment Analysis on Twitter Emotion Data

Tweets are difficult to classify due to their simplicity and frequent use of non-standard orthodoxy or slang words. Although several studies have identified highly accurate sentiment data classifications, most have not been tested on Twitter data. Previous research on sentiment interpretation focused on binary or ternary sentiments in monolingual texts. However, emotions emerge in bilingual and multilingual texts. The emotions expressed in today's social media, including microblogs, are different. We use a dataset that combines everyday dialogue, easy and emotional stimulation to carry out the algorithm to create a balanced dataset with five labels: joy, sad, anger, fear, and neutral. This entails the preparation of datasets and conventional machine learning models. We categorized tweets using the Bidirectional Encoder Representations from Transformers (BERT) language model but are pre-trained in plain text instead of tweets using BERT Transfer Learning (TensorFlow Keras). In this paper we use the HuggingFace’s transformers library to fine-tune pretrained BERT model for a classification task which is termed as modified (M-BERT). Our modified (M-BERT) model is an average F1-score of 97.63% in all of our taxonomy, which leaves more space for change, is our modified (M-BERT) model. We show that the dual use of an F1-score as a combination of M-BERT and Machine Learning methods increases classification accuracy by 24.92%. as related to baseline BERT model.