Fake Account Research Articles

Detecting Fake Accounts on Instagram Using Machine Learning and Hybrid Optimization Algorithms

In this paper, we propose a hybrid method for detecting fake accounts on Instagram by using the Binary Grey Wolf Optimization (BGWO) and Particle Swarm Optimization (PSO) algorithms. By combining these two algorithms, we aim to leverage their complementary strengths and enhance the overall optimization performance. We evaluate the proposed hybrid method using four classifiers: Artificial Neural Network (ANN), K-Nearest Neighbor (KNN), Support Vector Machine (SVM), and Logistic Regression (LR). The dataset for the experiments contains 65,329 Instagram accounts. We extract features from each account, including profile information, posting behavior, and engagement metrics. The Binary Grey Wolf and Particle Swarm Optimizations, when combined to form a hybrid method (BGWOPSO), improved the performance in accurately detecting fake accounts on Instagram.

An efficient fake account identification in social media networks: Facebook and Instagram using NSGA-II algorithm

An efficient fake account identification in social media networks: Facebook and Instagram using NSGA-II algorithm

FAKE PROFILE DETECTION ON SOCIAL NETWORKING WEBSITES USING MACHINE LEARNING

In an age where social media has become an integral part of our lives, the challenge of detecting fake accounts on platforms like Instagram has gained significant importance. This project, titled "Instagram Fake Account Detection using Machine Learning," employs Python as its primary tool to tackle this problem. It leverages two powerful machine learning algorithms, the Random Forest Classifier and the Decision Tree Classifier, to accomplish this task. The Random Forest Classifier demonstrates remarkable performance, achieving a 100% accuracy on the training dataset and an impressive 93% accuracy on the test dataset. Meanwhile, the Decision Tree Classifier exhibits its effectiveness with a training accuracy of 92% and a test accuracy of 92%. The dataset employed in this project is composed of 576 records, each characterized by 12 distinct features. These features encompass critical aspects of Instagram profiles, including the presence of a profile picture, the ratio of numerical characters in usernames, the breakdown of full names into word tokens, the ratio of numerical characters in full names, the equality between usernames and full names, the length of user bios, the existence of external URLs, the privacy status of accounts, the number of posts, the count of followers, the number of accounts followed, and the ultimate classification of an account as "Fake" or "Not." By harnessing the capabilities of Python and these advanced machine learning models, this project endeavors to provide a robust and efficient solution for the identification of fake Instagram accounts. In doing so, it contributes to the preservation of the platform's integrity and the security of its users.

Fake Profile Detection on Social Networking Websites Using Machine Learning

In an age where social media has become an integral part of our lives, the challenge of detecting fake accounts on platforms like Instagram has gained significant importance. This project, titled "Instagram Fake Account Detection using Machine Learning," employs Python as its primary tool to tackle this problem. It leverages two powerful machine learning algorithms, the Random Forest Classifier and the Decision Tree Classifier, to accomplish this task. The Random Forest Classifier demonstrates remarkable performance, achieving a 100% accuracy on the training dataset and an impressive 93% accuracy on the test dataset. Meanwhile, the Decision Tree Classifier exhibits its effectiveness with a training accuracy of 92% and a test accuracy of 92%. The dataset employed in this project is composed of 576 records, each characterized by 12 distinct features. These features encompass critical aspects of Instagram profiles, including the presence of a profile picture, the ratio of numerical characters in usernames, the breakdown of full names into word tokens, the ratio of numerical characters in full names, the equality between usernames and full names, the length of user bios, the existence of external URLs, the privacy status of accounts, the number of posts, the count of followers, the number of accounts followed, and the ultimate classification of an account as "Fake" or "Not." By harnessing the capabilities of Python and these advanced machine learning models, this project endeavors to provide a robust and efficient solution for the identification of fake Instagram accounts. In doing so, it contributes to the preservation of the platform's integrity and the security of its users.

Improved performance of fake account classifiers with percentage overlap features selection

Feature selection plays a crucial role in the development of high-performance classification models. We propose an innovative method for detecting fake accounts. This method leverages the percentage overlap technique to refine feature selection. We introduce our technique upon earlier work that showcased the enhanced efficacy of the Naïve Bayesian classifier through dataset normalization. Our study employs a dataset of account profiles sourced from Twitter, which we normalize using the Min-Max method. We analyze the results through a series of comprehensive experiments involving diverse classification algorithms—such as Naïve Bayes, decision tree, k-nearest neighbors (KNN), deep learning, and support vector machines (SVM). Our experimental results demonstrate a 100% accuracy achieved by the SVM and deep learning classifiers. The results are attributed to the percentage overlap technique, which facilitates the identification of four highly informative features. These findings outperform models with more extensive feature sets, underscoring the efficacy of our approach.

Blockchain Enabled Social Network for Detecting Fake Accounts

Front end technology with permanent accounts is employed in online social networks to help people get to know one another. In an effort to maintain connection with everyone, Facebook and Twitter are changing along with the users. OSNs are used by them for planning events, news exchange, interpersonal communication, and even running their own online enterprises. Because of OSNs' quick growth and the abundance of personal data that its users have shared, attackers and imposters have been lured to them with the intention of stealing personal information, spreading disruptive activities, and publishing false information. A further rationale for creating fictitious profiles for hateful accounts. In an attempt to harm the reputation of the person they detest, these users make profiles using their usernames and publish photographs and articles that aren't related to them. to use blockchain technology, Aadhar number verification, and SVM profile classification to create a reliable solution for detecting phoney social network profiles. By analysing several aspects of social media profiles, the SVM classification uses machine learning to discern between real and fraudulent accounts. By verifying Aadhar numbers through legitimate channels, Aadhar number verification is integrated into the registration process, guaranteeing the authenticity of user identities. A decentralised and secure identity management system is made possible by the use of blockchain technology, with smart contracts providing immutable storage for verified user data.

Cyberbullying and Fake Account Detection on Social Media Using Machine Learning and NLP

Now a days the use of social media has grown exponentially with the simultaneous growth of the internet throughout the world and it is mostly attracted by the youth. However, the enhancement of social connectivity by using this social media platform may also lead to a negative impact on society mainly cybercrime, cyberbullying, abuse, etc. This cyberbullying is a major problem in this society which leads to frequent physical and mental stress, particularly for teenagers, transgenders, and women. Cyberbullying is done by using comments on social media platforms commenting vulgar words and also due to the increase of user’s various malicious entities like increasing fake accounts increased a lot. Detection of cyberbullying and fake accounts on such large platforms is very difficult and may sometimes lead to false detection. So many incidents have recently occurred throughout the world like suicides, mental illness, etc. So our goal is to identify bullying comments and fake accounts on social media platforms like Facebook, Twitter, etc. By merging natural language processing and machine learning algorithms like xgboost(extreme gradient boosting) to detect fake accounts and logistic regression for cyberbullying. Key Words: Cyberbullying, Natural language processing, Machine learning, xgboost(extreme gradient boosting), logistic regression, Random forest, etc.

Advanced Machine Learning Techniques for Fake Account Detection in Online Platforms: A Comprehensive Analysis and Novel Approach

Advanced Machine Learning Techniques for Fake Account Detection in Online Platforms: A Comprehensive Analysis and Novel Approach

The Potential Hazards of Fake Accounts and Buzzer Behaviour on Deliberative Democracy

The most famous political system globally is deliberative democracy, which involves the participatory engagement of free and fair citizens to achieve common interests through discussion-based reasoning and societal consensus. This system places all citizens on an equal footing in expressing their opinions and is a crucial indicator of the quality of deliberative democracy. The dynamics of deliberative democracy are also mirrored in the digital realm and often serve as indicators of public support. However, the digital sphere of democracy faces a severe threat today due to the proliferation of fake accounts and the practice of paying for buzzer behaviour. This phenomenon necessitates stringent regulation to ensure the continued quality and authenticity of deliberative democracy. This research describes the potential dangers of using fake accounts and paying for buzzer behaviour in politics concerning deliberative democracy. The researchers adopted an interpretive phenomenology approach, drawing data from various relevant sources. The research findings reveal that using fake accounts and paying for buzzer behaviour undermine deliberative democracy as they generate false information, manipulate public opinion, and hinder healthy dialogue. Additionally, using fake accounts and buzzer behaviour has severe psychological and social repercussions, including a decline in public trust and an increase in political polarization, all threatening the quality of democratic decision-making. The results of this research carry significant implications for designing relevant regulations to safeguard the agreed-upon and high-quality deliberative democracy, a vital asset of public governance. Keywords: Fake accounts, buzzer behaviour, cyber trooper, deliberative democracy, virality.

Use of Machine Learning to Identify Fake Profiles

Abstract: These days, social media plays a big role in our everyday lives. Presently, over 50% of the global population actively utilizes social media sites. The prevalence of fraudulent accounts on social platforms is a serious problem that has been brought about by their ever-growing popularity. The goal of these fictitious accounts is to mimic or deceive other people. They are now a simple means of deceiving consumers into purchasing phony goods and services. Additionally, billions of people's personal information is in jeopardy. It is now crucial to identify and disable the phony accounts before any damage is done because of these dangers. Thanks to machine learning, it's now simple to identify millions of these accounts automatically. Users fabricate profiles to disseminate false information, including hate speech, rumors, texts from bullied individuals, and more. Researchers used deep learning and machine learning models to propose some strategies to mitigate this problem, yet a large number of phony accounts remain. These phony accounts are unacceptable for a respectable social networking site, nevertheless. This article provides an overview of the latest developments in social networking fake account identification

A Fake Profile Detection Model Using Multistage Stacked Ensemble Classification

Fake profile identification on social media platforms is essential for preserving a reliable online community. Previous studies have primarily used conventional classifiers for fake account identification on social networking sites, neglecting feature selection and class balancing to enhance performance. This study introduces a novel multistage stacked ensemble classification model to enhance fake profile detection accuracy, especially in imbalanced datasets. The model comprises three phases: feature selection, base learning, and meta-learning for classification. The novelty of the work lies in utilizing chi-squared feature-class association-based feature selection, combining stacked ensemble and cost-sensitive learning. The research findings indicate that the proposed model significantly enhances fake profile detection efficiency. Employing cost-sensitive learning enhances accuracy on the Facebook, Instagram, and Twitter spam datasets with 95%, 98.20%, and 81% precision, outperforming conventional and advanced classifiers. It is demonstrated that the proposed model has the potential to enhance the security and reliability of online social networks, compared with existing models.

Deep neural networks approach with transfer learning to detect fake accounts social media on Twitter

<span>The massive use of social media makes people take actions that have a negative impact on cyberspace, such as creating fake accounts that aim to commit crimes such as spam and fraud to spread false information. Fake accounts are difficult to detect in the traditional way because fake accounts always use photos, names, and unreal information, there are several criteria that can identify a fake account such as no information, few followers, and minimal activity. In the traditional model, it is difficult to detect fake accounts on many Twitters social media accounts, so the application of the deep learning model with the convolutional neural network (CNN) algorithm and the application of deep learning can help detect fake accounts. This study will use data on Twitter social media so that this research produces good accuracy for the scenarios described at the methodology stage. This research produces an accuracy of 86% for the deep learning model with the CNN algorithm, and with the traditional model, it produces an accuracy of 51% while the use of transfer learning produces an accuracy of 93.9%.</span>

Machine learning for detecting fake accounts and genetic algorithm-based feature selection

Abstract People rely extensively on online social networks (OSNs) in Africa, which aroused cyber attackers’ attention for various nefarious actions. This global trend has not spared African online communities, where the proliferation of OSNs has provided new opportunities and challenges. In Africa, as in many other regions, a burgeoning black-market industry has emerged, specializing in the creation and sale of fake accounts to serve various purposes, both malicious and deceptive. This paper aims to build a set of machine-learning models through feature selection algorithms to predict the fake account, increase performance, and reduce costs. The suggested approach is based on input data made up of features that describe the profiles being investigated. Our findings offer a thorough comparison of various algorithms. Furthermore, compared to machine learning without feature selection and Boruta, machine learning employing the suggested genetic algorithm-based feature selection offers a clear runtime advantage. The final prediction model achieves AUC values between 90% and 99.6%. The findings showed that the model based on the features chosen by the GA algorithm provides a reasonable prediction quality with a small number of input variables, less than 31% of the entire feature space, and therefore permits the accurate separation of fake from real users. Our results demonstrate exceptional predictive accuracy with a significant reduction in input variables using the genetic algorithm, reaffirming the effectiveness of our approach.

Unmasking deceptive profiles: A deep dive into fake account detection on instagram and twitter

The rise of online social networks, also known as OSNs, has captured the attention of younger generations and made them an integral part of social life. As a result, the use of various social media platforms has increased significantly, greatly impacting individuals' social connections. These platforms offer a wide range of features, such as news distribution, contributing to their widespread use. However, with the rapid growth of social media, the prevalence of fake accounts has become a major problem, posing a threat to both the security of users and the integrity of these platforms. In response, this article explores the effectiveness of machine learning algorithms (ML). Detect and identify fraudulent accounts on popular social media platforms, especially Instagram and Twitter. Our methodology involves analyzing user activity and account information to develop fine-tuned machine-learning models. Our approach takes into account important parameters such as number of followers, number of posts, and engagement.

Detection of Fake Accounts on Social Media Using Multimodal Data With Deep Learning

Detection of Fake Accounts on Social Media Using Multimodal Data With Deep Learning

Фэйк-аккаунттарды анықтау мәселесінде машиналық оқытуды қолдану

Nowadays, due to the rapid growth of social networks, the possibility of various threats is increasing, one of which is fake accounts. The use of machine learning in the issue of identifying fake accounts on a social network is considered. The main goal of the work is to research and develop methods and models of machine learning for the effective detection of fake accounts in social networks. This avoids problems such as extortion, blackmail, harassment, fake requests, insulting a person, unauthorized access to personal information, illegal use of user information through research. The object of the study is fake accounts. Methods used in the research work: scaling methods, machine learning methods, feature selection methods, model evaluation methods. The subject area of the research work is Instagram. The uniqueness of the study is to determine the most reliable way to detect fake accounts using various, widely used methods. Machine learning classifiers were effectively used to detect a fake account: decision tree classifier; classifier KNN; logistic regression classifier; random forest classifier; support vector machine (SVM) classifier. The performance of the models was evaluated using various indicators, such as accuracy, ROC-curve, classification score. Some models, such as Decision Tree, Random Forest, and KNN, have shown stable and high AUC-ROC, Accuracy, Precision, Recall, and F1 scores both during initial testing and after retraining. This highlights the importance of choosing the right features when training a model and shows that not all features are equally useful for all models. As a result of the study, after verifying the effectiveness of using machine learning algorithms to identify fake

Social Media Fake Account Identification Using Machine Learning

The proliferation of social media platforms has led to an increase in the creation of fake accounts. These accounts are used for various malicious activities, such as spreading false information, phishing, and identity theft. As a result, there is a growing need for effective methods to identify and eliminate fake accounts. This paper proposes a machine learning-based approach for social media fake account identification. The proposed method involves pre-processing the data, feature extraction, and training a classifier using various machine learning algorithms. The performance of the proposed method is evaluated using a publicly available dataset and compared with existing methods. The results demonstrate the effectiveness of the proposed approach in identifying fake accounts with high accuracy and low false positive rates.

Fake account detection in social media using machine learning methods: literature review

With the rapid development of emerging technologies in the industrial revolution 4.0 or 5.0, social media has become one of the social environments to carry out social activities, both socializing and advertising. However, since it is an open platform by nature, cybercrime occurrence in social media is inevitable. Currently, more than a million fake accounts are existing on Instagram, Twitter, and Facebook, intending to increase followers, spread hoaxes, and spam. On one hand, it is difficult to manually eliminate these accounts on social media platforms. On the other hand, research on automatic fake account detection has been carried out for more than a decade. This study provides literature reviews aiming to deliver information about several methods and machine learning algorithms with the performances measured in identifying fake accounts on three well-known social media platforms: Twitter, Instagram, and Facebook.

Touch and Go

This issue of Screen Bodies features articles that contribute to a group of closely related critical concerns, namely, the existential and political significance of tacticity, feeling, and the representation of embodied experience. In her article, “Feeling Like Death,” Caitlin Wilson examines the aesthetic strategies Agnes Varda employs in two early films, La Pointe Courte (1955) and Le Bonheur (1965), that emphasize “textures and tactility” in the portrayal of mortality, death, and mourning. Wilson shows how Varda uses haptic imagery and calculated cinematic techniques to convey an experience of grief that is “palpable as well as visible.” Wilson persuasively argues that Varda depicts the embodied feeling of mortality to create a heightened sense of intimacy between the films’ characters. Similarly, in her timely article, “Gut Feelings,” Jennifer Jasmine White argues that Sheena Patel challenges the trend towards emotional indifference or “flatness” in the emerging genre of “internet novels.” In contrast to the affectless, numb, and apathetic heroine characteristic of novels like Lauren Oyler's Fake Accounts (2021) and Ottessa Moshfegh's My Year of Rest and Relaxation (2018), Patel's I'm a Fan (2022) features a more realistically emotional protagonist. White argues that the novel functions as an intervention that opposes affective indifference and the political apathy it inspires. She writes that most examples of the so-called internet novel, that is, literature that focuses on social media, influencer culture, and characters who are chronically online, suggest highly mediated social experience leads to emotional and political malaise. Patel rejects this trend and instead centers “the feeling body,” the embodied experience of life online, and the political agency it fosters.

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.