Fake Social Media Research Articles

A new sociology of humans and machines.

From fake social media accounts and generative artificial intelligence chatbots to trading algorithms and self-driving vehicles, robots, bots and algorithms are proliferating and permeating our communication channels, social interactions, economic transactions and transportation arteries. Networks of multiple interdependent and interacting humans and intelligent machines constitute complex social systems for which the collective outcomes cannot be deduced from either human or machine behaviour alone. Under this paradigm, we review recent research and identify general dynamics and patterns in situations of competition, coordination, cooperation, contagion and collective decision-making, with context-rich examples from high-frequency trading markets, a social media platform, an open collaboration community and a discussion forum. To ensure more robust and resilient human-machine communities, we require a new sociology of humans and machines. Researchers should study these communities using complex system methods; engineers should explicitly design artificial intelligence for human-machine and machine-machine interactions; and regulators should govern the ecological diversity and social co-development of humans and machines.

Fake Social Media Profile Detection

The proliferation of fake social media profiles has become a significant concern, posing risks such as, identity theft and any other malicious action as well as fraud, have become critically alarming. This project focuses on designing an integrated system that aggregates and presentsinformation considered important to any social media account: activity patterns, connection history, and content authenticity. The system will help in providing a detailed profile analysis of account holders, thus enabling the users to identify suspicious accounts and report such accounts for further action by the authorities. The given solution will complement the safety of the platform, ensure informed decision-making, and contribute to the mitigation of such risks by eliminating fake accounts and malicious activities from the digital space.

Characteristics and Prevalence of Fake Social Media Profiles with AI-generated Faces

Characteristics and Prevalence of Fake Social Media Profiles with AI-generated Faces

Fake social media news and distorted campaign detection framework using sentiment analysis & machine learning

Social networking platforms have become one of the most engaging portals on the Internet, enabling global users to express views, share news and campaigns, or simply exchange information. Yet there is an increasing number of fake and spam profiles spreading and disseminating fake information. There have been several conscious attempts to determine and distinguish genuine news from fake campaigns, which spread malicious disinformation among social network users. Manual verification of the huge volume of posts and news disseminated via social media is not feasible and humanly impossible. To overcome the issue, this research presents a framework to use sentiment analysis based on emotions to investigate news, posts, and opinions on social media. The proposed model computes the sentiment score of content-based entities to detect fake or spam and detect Bot accounts. The authors also present an investigation of fake news campaigns and their impact using a machine learning algorithm with highly accurate results as compared to other similar methods. The results presented an accuracy of 99.68 %, which is significantly higher as compared to other methodologies delivering lower accuracy.

Misinformation as a Determinant of Response to COVID 19

Abstract Most of the micro and macro effects of the COVID-19 pandemic on the global economy have been investigated in the past two years. Few studies have examined COVID disinformation in non-Western countries. India produced the most social media disinformation, probably due to its high internet penetration, increased social media consumption, and low internet literacy (Al-Zaman, 2022a). To quantify the influence of disinformation on pandemic response, this study used mixed methods. The variables were examined through in-depth interviews. As they use digital media more than others, participants under 40 provided quantifiable data (The Future of India Foundation. (2022). Politics of disinformation: Why the current approaches are geared to fail and possible path forward. Retrieved from https://futureofindia.in/reports). It is mainly collected from metro cities of India. Moderation analysis using PLS-SEM examined whether self-perceived media literacy moderates the link between fake social media news and COVID-19 anxiety. The study findings have been linked to the theoretical foundation, the availability heuristic. This study holds significance as its implications will be beneficial in tackling the challenges associated with misinformation and its influence on response to pandemics that might be experienced in the future.

Faking the war: fake posts on Turkish social media during the Russia–Ukraine war

This study aims to analyze the fake posts circulated on Turkish social media during the Russia–Ukraine war. With advancing technology, social media platforms have a profound impact on the way we perceive and interpret events and make us question the accuracy of information generated about international events such as wars. While the Russia–Ukraine war constitutes an important turning point in international relations, the reflection of these events on social media is also seen in fake posts. In this context, the main purpose of this study is to identify the common themes of fake social media posts and to reveal the general context of these posts on social media. In addition, the study aims to analyze the fake content circulating on Turkish social media and to reveal the emerging polarized discourses through the identified themes. The research revolves around five main themes that feed polarization: war reporting, ideological misrepresentation, humor, hate speech, and conspiracy theories. The findings show that fake content is particularly concentrated around ideological polarization and antagonisms. It was also found that misinformation and decontextualized humor blurred the true context of the war and that fake content combined with hate speech and conspiracy theories distorted the context of the war.

Fake Social Media News Detection Based on Forwarding User Representation

Fake Social Media News Detection Based on Forwarding User Representation

Fake Social Media Post Detection by Using Deep Learning Algorithm

In today's digital age, social media serves as both a boon and a bane, offering immense opportunities for personal growth while also being a breeding ground for misinformation and deception. The rise of sophisticated multimedia manipulation techniques has blurred the line between reality and fiction, presenting significant challenges to discerning genuine content from fabricated ones. This paper presents an overview of the escalating threat posed by fake posts on social media and proposes a novel approach for their detection. The proposed method leverages advanced technologies such as Error Level Analysis (ELA) and Convolutional Neural Networks (CNNs) to distinguish between authentic and manipulated posts. Unlike traditional approaches reliant on manual feature extraction, our framework employs deep learning methodologies for more nuanced pattern recognition and generalization to unseen data. By combining ELA for initial image analysis and CNNs for deep feature extraction, followed by classification using Support Vector Machines (SVMs) and K-Nearest Neighbors (KNNs), we achieve robust detection of fake images .Experimental results demonstrate the effectiveness of our approach, with a peak accuracy of 91.3% using Residual Networks and KNN. This method offers a promising solution to mitigate the proliferation of fake images on social media platforms, thereby combating the spread of misinformation, propaganda, and chaos.

Application to Detect Fake Social Media Profile & Verification Using Block Chain Technology

This paper proposes a novel social media platform that leverages blockchain technology to address the rising concerns of fake profiles and privacy violations. Our system prioritizes robust identity verification through a decentralized approach and immutable user data storage on a blockchain ledger. By eliminating centralized control and single points of failure, the platform enhances trust and security in online interactions. Additionally, we integrate government-issued ID verification (e.g., Aadhaar card) through smart contracts to add an extra layer of trust and strengthen user profiles. This paper details the design, implementation, and functionalities of the proposed system, aiming to showcase its effectiveness in revolutionizing online identity verification within social media applications

Fake Social Media Profile Detection and Reporting Using Machine Learning

Our research focuses on utilizing machine learning techniques, encompassing natural language processing and computer vision, to create an automated system for the detection and reporting of fake social media profiles across various platforms. Our approach involves feature extraction from both textual and visual content, followed by the application of machine learning models to classify profiles as fake or genuine. This system operates in real-time, monitoring user activity and promptly flagging suspicious profiles for user- initiated reporting. By combining the power of machine learning with cross-platform compatibility and user feedback, our solution aims to enhance online safety by swiftly identifying and addressing fraudulent social media profiles, thus fostering more secure and trustworthy online communities.

Leveraging Machine Learning for Fraudulent Social Media Profile Detection

Abstract Fake social media profiles are responsible for various cyber-attacks, spreading fake news, identity theft, business and payment fraud, abuse, and more. This paper aims to explore the potential of Machine Learning in detecting fake social media profiles by employing various Machine Learning algorithms, including the Dummy Classifier, Support Vector Classifier (SVC), Support Vector Classifier (SVC) kernels, Random Forest classifier, Random Forest Regressor, Decision Tree Classifier, Decision Tree Regressor, MultiLayer Perceptron classifier (MLP), MultiLayer Perceptron (MLP) Regressor, Naïve Bayes classifier, and Logistic Regression. For a comprehensive evaluation of the performance and accuracy of different models in detecting fake social media profiles, it is essential to consider confusion matrices, sampling techniques, and various metric calculations. Additionally, incorporating extended computations such as root mean squared error, mean absolute error, mean squared error and cross-validation accuracy can further enhance the overall performance of the models.

Detecting Fake Social Media Profiles Using the Majority Voting Approach

INTRODUCTION: The rise of social media platforms has brought about a concerning surge in the creation of fraudulent user profiles, with intentions ranging from spreading false information and perpetrating fraud to engaging in cyberbullying. The detection of these deceptive profiles has emerged as a critical imperative to safeguard the trustworthiness and security of online communities.OBJECTIVES: This paper focused on the detection and identification of fake social media profiles.METHODS: This paper introduces an innovative approach for discerning and categorizing counterfeit social media profiles by leveraging the majority voting approach. The proposed methodology integrates a range of machine learning algorithms, including Decision Trees, XGBoost, Random Forest, Extra Trees, Logistic Regression, AdaBoost and K-Nearest Neighbors each tailored to capture distinct facets of user behavior and profile attributes. This amalgamation of diverse methods results in an ensemble of classifiers, which are subsequently subjected to a majority voting mechanism to render a conclusive judgment regarding the legitimacy of a given social media profile.RESULTS: We conducted thorough experiments using a dataset containing both legitimate and fake social media profiles to determine the efficiency of our methodology. Our findings substantiate that the Majority Voting Technique surpasses individual classifiers, attaining an accuracy rate of 99.12%, a precision rate of 99.12%, a recall rate of 99.12%, and an F1-score of 99.12%.CONCLUSION: The results show that the majority vote method is reliable for detecting and recognising fake social media profiles.

Politics of Vengeance in Iranian Diaspora Communities

The death of the young Kurdish Iranian woman, Mahsa Jina Amini, on September 16, 2022 following her arrest by Iran's now-suspended Gasht-i Irshad (guidance patrol or morality police) for apparent lax conformity to the Islamic dress code ignited protests across Iran. The protests, known as Women, Life, Freedom (Zan, Zendegī, Azadi) quickly spread to Iranian diaspora communities across North America, Europe, and Australia. Initially, diasporic Iranians organized their protests to support and amplify their compatriots’ calls for justice. As the protests continued in Iran and the demands for change grew louder, some members of the Iranian diaspora shifted their focus from the Islamic Republic to the public shaming of Iranians living outside Iran for their purported support of the Iranian regime. Some of the tactics employed by those engaged in public humiliations of suspected regime supporters recalled Gasht-i Irshad's methods of trapping and accosting individuals for perceived infractions. These public confrontations were aimed at isolating, shaming, and silencing perceived allies of the Islamic Republic and, by extension, denouncing the regime for its abrogation of women's and human rights. I refer to this phenomenon among diasporic Iranians as gasht-i intiqām, roving avengers, which reflects a frustration with the absence of justice in Iran and targets purported proxies for the regime. There have been many instances and types of denunciations aimed at silencing and ostracizing individuals, academics, and institutions. As Daniel Block points out in his analysis, “The attacks overwhelmingly target women, most notably in North America and Europe. The victims include gender equality activists, journalists, foreign policy analysts and a historian, each of whom has been accused of colluding with the authoritarian Islamist regime in Tehran.” Block further points out that many of the attacks are anonymous or originate from fake social media accounts. The common denominator he finds among those who target individuals is opposition to “Western-Iranian diplomacy or reporting information that adds subtlety to the debate over how the United States and its allies should handle the Islamic Republic.”1 Often those deemed regime collaborators are Iranian American individuals, journalists, or institutions that supported the 2015 the Joint Comprehensive Plan of Action, otherwise known as the nuclear deal.

A Dynamic Ensemble Selection of Deepfake Detectors Specialized for Individual Face Parts

The development of deepfake technology, based on deep learning, has made it easier to create images of fake human faces that are indistinguishable from the real thing. Many deepfake methods and programs are publicly available and can be used maliciously, for example, by creating fake social media accounts with images of non-existent human faces. To prevent the misuse of such fake images, several deepfake detection methods have been proposed as a countermeasure and have proven capable of detecting deepfakes with high accuracy when the target deepfake model has been identified. However, the existing approaches are not robust to partial editing and/or occlusion caused by masks, glasses, or manual editing, all of which can lead to an unacceptable drop in accuracy. In this paper, we propose a novel deepfake detection approach based on a dynamic configuration of an ensemble model that consists of deepfake detectors. These deepfake detectors are based on convolutional neural networks (CNNs) and are specialized to detect deepfakes by focusing on individual parts of the face. We demonstrate that a dynamic selection of face parts and an ensemble of selected CNN models is effective at realizing highly accurate deepfake detection even from partly edited and occluded images.

A Comparative Analysis of Ensemble Learning Methods on Social Media Account Detection

Today, social media platforms usage and benefiting rate from these environments are increasing. This rapid spread of social media has also allowed the emergence of fake accounts. Fake accounts are generally created to implement malicious activities through another user account or to spread incorrect information. To prevent the detriment that this situation may cause to real individuals, an effective fake account detection was carried out by using ensemble learning methods (Bagging, Boosting, Stacking, Voting and Blending) in this study. These methods were combined with various machine learning algorithms to measure their effectiveness in detecting fake accounts. The experimental results suggested that Bagging technique attained an accuracy level of 90.441%, Stacking technique 89.706%, Voting technique 88.971% and the Blending technique attained 88.235% in the test phase. While for the Boosting methods, XGboost technique attained accuracy level of 86.765%, whereas the AdaBoost outperformed it with an accuracy level of 91.912% in the test phase. The extant results demonstrates that ensemble learning methods combined with machine learning algorithms are efficient in detecting fake social media accounts. It is considered that additional studies with larger datasets alongside the usage of different ensemble methods can further improve the accuracy of the detection process.

JURIDICAL ANALYSIS OF JUDGE'S DECISIONS IN THE CRIME OF THREATENING AND FRIGHTENING ADDRESSED PERSONALLY

In addition to having a positive impact, technology also has a negative impact on society, including the emergence of more and more new crimes, namely computer crimes, such as internet fraud, hacking of ATM PIN, burglary of banking accounts, the rise of fake social media, pornographic media, and defamation through the internet. This study aims to legally analyze the judge's decision in the criminal act of threats and intimidation directed personally related to Law Number 11 of 2008. This study uses a descriptive analysis method with a normative juridical approach. The reference for the panel of judges in deciding cases is the prosecutor's indictment, not the indictment by taking into account the evidence. The judge's considerations are deemed appropriate to be able to sentence the defendant. Regulations and sanctions for all forms of social media use must be in line with the ideals in which Law Number 11 of 2008 was made to protect and maintain the comfort of social media users. So that in the future social media users can use it wisely to build a modern and law-abiding society. In this case law enforcers must see that the use of social media is increasingly being used at this time, this causes the use of social media to become uncontrollable, causing losses to the parties.
 

Machine and Deep Learning Studies for Cyberbullying Detection

The internet revolution in society has various effects on our daily life such as the use of social media. While social media is ubiquitous and great in some aspects, it brings a new issue that appears more and more in today’s world. This new issue, Cyberbullying, involves harming someone by posting or sharing content that causes feelings of embarrassment, guilt, or humiliation. Easily creating fake social media accounts with fake identity further increase cyberbullying incidents and encourages cyberbullies. Cyberbullying can affect people both mentally and physically and can lead to permanent problems. However, studies in this area show that cyberbullying can be prevented. In this study, we review machine learning techniques to detect and prevent cyberbullying, evaluate the performances of the machine and deep learning models, and examine factors that affect the performance of the models. We also discuss the importance of data preprocessing, feature extraction and selection, and classification processes in cyberbullying detection problems.

Self-breeding Fake News

Studies have found that artificial intelligence (AI) bots and cookies automate fake news in zones of social conflict such as race, religion, gender, and class. In this background, this paper investigates whether fake news is automated with the social structure unique to India. The research collected campaigning activities of political parties and politicians on the Internet but was limited to a select number of Facebook profiles, websites, hashtags, and Twitter profiles during India’s 2014 and 2019 general elections. Politicians and political parties on Twitter, Facebook and other websites formed the contact points where empirical data were collected in the research design. By reviewing hashtags such as #Nationwantsrammandir; #NaamVaapsi; #RamMandir; #AntiNationals; #caste; and #Hindutva, as well as fake social media accounts; discussion forums; and profiles of followers of politicians, the paper corroborated that bots, AI, and trolls serve fake news in the conflict zones of India and some forces are using it to perpetuate social divisions based on caste, class, religion, gender, and region. This paper argues that automated social media accounts spread false information that likely polarizes social conflicts in India.

Digital Authoritarianism in the Middle East: Deception, Disinformation and Social Media

Digital Authoritarianism in the Middle East: Deception, Disinformation and Social Media

Information items used by online fraudsters and its relationship to Indonesian digital literacy

Introduction. This research was conducted to examine the information items used by online fraudsters related to the level of digital literacy of the society. This research was done on the pillars of data security in digital literacy.
 Data Collection Methods. Data was collected by watching videos on Youtube, online interviewing people who complained about the fraud they experienced on Facebook and Whatsapp in the period of 2019-2022.
 Data Analysis. The data was descriptively analyzed and classified to describe information items used by the fraudsters.
 Results and Discussion. The items used by the fraudsters are banking service terms, real but fake URLs, police standard operating procedures, and English terms used by market place. Therefore, continuous socialization from institutions related to these items of information is needed to improve digital literacy of society which has the potential to cause financial losses. In terms of socialization, libraries can play a proactive role.
 Conclusion. Information items that often used by online fraudsters are information related to banking services, police, marketplace, and fake social media accounts. This research may be continued to understand how low the victims' ignorance about the information items.