Spammers In Social Networks Research Articles

ALBERT4Spam: A Novel Approach for Spam Detection on Social Networks

Engaging in social media browsing stands out as one of the most prevalent online activities. As social media increasingly integrates into our daily routines, it opens up numerous opportunities for spammers seeking to target individuals through these platforms. Given the concise and sporadic nature of messages exchanged on social networks, they fall within the realm of short text classification challenges. Effectively addressing such issues requires appropriately representing the text to enhance classifier efficiency.Accordingly, this study utilizes robust representations derived from contextualized models as a component of the feature extraction process within our deep neural network model, which is built upon the Bidirectional Long Short-Term Memory neural network (BLSTM). Introducing ALBERT4Spam, the study presents a deep learning methodology aimed at identifying spam on social networking platforms. It harnesses the proven ALBERT model to acquire contextualized word representations, thereby elevating the effectiveness of the suggested neural network framework.The random search method was used to fine-tune the ALBERT4Spam model's hyperparameters, which included the number of BLSTM layers, neuron count, layer count, activation function, weight initializer, learning rate, optimizer, and dropout, in order to obtain optimal performance. The experiments conducted on three benchmark datasets demonstrate that our innovative model surpasses widely used methods in social network spam detection. The precision results stand at 0.98, 0.96, and 0.98 for Twitter, YouTube, and SMS datasets, respectively, showcasing superior performance outcomes.

Spam Detection in Social Networks Using Machine Learning Algorithms

Social networking websites have become more and more popular recently. Users use them to meet new people and communicate their most recent thoughts and actions to their existing acquaintances. The website among these that is growing the quickest is social media. Due to its popularity, many spammers attempt to flood actual users' accounts with spam messages. This paper considers three social networks, Twitter, Facebook, and Instagram, for experimentation. The classification of the data into spam and non-spam using four machine learning techniques, including SVM, KNN, decision trees, and Random Forest. The results obtained from the experiments show that the proposed approach can accurately detect spam in social networks. Implementing such algorithms could help social network platforms improve user experience by reducing the prevalence of spam and fraudulent activity

Evaluating the Performance of Heterogeneous and Homogeneous Ensemble-based Models for Twitter Spam Classification

Spam based attacks are growing in various social networks. Social network spam is a type of unwanted content that appears on social networking sites, such as Facebook, Twitter, Instagram, and others. This study used two categories of ensemble algorithms to build Twitter spam classification models. These algorithms worked by combining the strengths of individual learning algorithms and then reporting their total performances. In ensemble learning, models are formed from data based on the assumption that combining the output of multiple models is better than using a single classifier. Hence, this study used a labeled public dataset for machine learning-based Twitter spam detection. Several studies have investigated the classification of Twitter spam from the available datasets. However, there is a paucity of works that investigated how machine learning-based models, built with homogenous and heterogeneous algorithms, behave in Twitter spam classification. ANOVA-F test was used for selecting the most promising features in the dataset. Then, homogeneous tree-based Random Forest (RF) ensemble and a heterogeneous ensemble vote classifier were employed for the classification of Twitter spam. Tree-based algorithms were used to build a homogeneous twitter spam detection model, while a combination of Support Vector Machine (SVM) and Decision Tree (DT) algorithms was used for building the heterogeneous model (using maximum voting classifier). The current study found that the performance of the Twitter spam detection models were promising. In all, the heterogeneous model recorded better performance with regards to accuracy, precision, recall, and F1-score than the model built with homogeneous base classifier.

Stratified hyperparameters optimization of feed-forward neural network for social network spam detection (SON2S)

Stratified hyperparameters optimization of feed-forward neural network for social network spam detection (SON2S)

Stochastic Gradient Boosting Model for Twitter Spam Detection

In today’s world of connectivity there is a huge amount of data than we could imagine. The number of network users are increasing day by day and there are large number of social networks which keeps the users connected all the time. These social networks give the complete independence to the user to post the data either political, commercial or entertainment value. Some data may be sensitive and have a greater impact on the society as a result. The trustworthiness of data is important when it comes to public social networking sites like facebook and twitter. Due to the large user base and its openness there is a huge possibility to spread spam messages in this network. Spam detection is a technique to identify and mark data as a false data value. There are lot of machine learning approaches proposed to detect spam in social networks. The efficiency of any spam detection algorithm is determined by its cost factor and accuracy. Aiming to improve the detection of spam in the social networks this study proposes using statistical based features that are modelled through the supervised boosting approach called Stochastic gradient boosting to evaluate the twitter data sets in the English language. The performance of the proposed model is evaluated using simulation results.

Discovering Spammers in Social Networks

As the popularity of the social media increases, as evidenced in Twitter, Facebook and China's Renren, spamming activities also picked up in numbers and variety. On social network sites, spammers often disguise themselves by creating fake accounts and hijacking normal users' accounts for personal gains. Different from the spammers in traditional systems such as SMS and email, spammers in social media behave like normal users and they continue to change their spamming strategies to fool anti spamming systems. However, due to the privacy and resource concerns, many social media websites cannot fully monitor all the contents of users, making many of the previous approaches, such as topology-based and content-classification-based methods, infeasible to use. In this paper, we propose a novel method for spammer detection in social networks that exploits both social activities as well as users' social relations in an innovative and highly scalable manner. The proposed method detects spammers following collective activities based on users' social actions and relations. We have empirically tested our method on data from Renren.com, which is the largest social network in China, and demonstrated that our new method can improve the detection performance significantly.

Advances in spam detection for email spam, web spam, social network spam, and review spam: ML-based and nature-inspired-based techniques

Despite the great advances in spam detection, spam remains a major problem that has affected the global economy enormously. Spam attacks are popularly perpetrated through different digital platforms with a large electronic audience, such as emails, microblogging websites (e.g. Twitter), social networks (e.g. Facebook), and review sites (e.g. Amazon). Different spam detection solutions have been proposed in the literature, however, Machine Learning (ML) based solutions are one of the most effective. Nevertheless, most ML algorithms have computational complexity problem, thus some studies introduced Nature Inspired (NI) algorithms to further improve the speed and generalization performance of ML algorithms. This study presents a survey of recent ML-based and NI-based spam detection techniques to empower the research community with information that is suitable for designing effective spam filtering systems for emails, social networks, microblogging, and review websites. The recent success and prevalence of deep learning show that it can be used to solve spam detection problems. Moreover, the availability of large-scale spam datasets makes deep learning and big data solutions (such as Mahout) very suitable for spam detection. Few studies explored deep learning algorithms and big data solutions for spam detection. Besides, most of the datasets used in the literature are either small or synthetically created. Therefore, future studies can consider exploring big data solutions, big datasets, and deep learning algorithms for building efficient spam detection techniques.

Editorial

Each year up to 1% of the papers published during the previous year are selected for the IEEE Systems Journal's Best Paper Award. The selection process is based on evaluations made by the reviewers and the Associate Editor. All Editorial Board members are involved in the process, although the Editor-in-Chief’s role is to monitor the process. Last April, five papers published during 2020 were selected for the IEEE Systems Journal's Best Paper Award, and the authors of the papers were subsequently notified accordingly. Given the large number of high-quality papers published in this journal, the Selection Committee had a difficult choice to make again this year; I take this opportunity to thank each committee member for your hard work. As with previous issues of the IEEE Systems Journal, this issue also contains numerous applications of complex systems and system of systems. The topics include hybrid brain/neural control, brain-machine interface, wireless sensor networks for healthcare applications, human action recognition, reducing the spread of spam in social networks, smart manufacturing systems, energy harvesting networks, secure industrial IoT, renewable energy sources in power grids, DC nanogrids, cybersecurity in smart grids, next-generation satellite systems, vehicle-to-vehicle communication, connected vehicles in long tunnels, indoor wireless communication, infrastructure-free indoor navigation (as represented by the cover picture), and many more. Several of these papers tackle emerging technologies, and we sincerely hope that they will help the systems community in advancing these rapidly growing research areas for the benefit of humanity

Social Network Spam Detection Based on ALBERT and Combination of Bi-LSTM with Self-Attention

Social networks are full of spams and spammers. Although social network platforms have established a variety of strategies to prevent the spread of spam, strict information review mechanism has given birth to smarter spammers who disguise spam as text sent by ordinary users. In response to this, this paper proposes a spam detection method powered by the self-attention Bi-LSTM neural network model combined with ALBERT, a lightweight word vector model of BERT. We take advantage of ALBERT to transform social network text into word vectors and then input them to the Bi-LSTM layer. After feature extraction and combined with the information focus of the self-attention layer, the final feature vector is obtained. Finally, SoftMax classifier performs classification to obtain the result. We verify the excellence of the model with accuracy, precision, F1-score, etc. The results show that the model has better performance than others.

Hyperparameter tuning of AdaBoost algorithm for social spammer identification

Purpose The purpose of this paper is to enhance the performance of spammer identification problem in online social networks. Hyperparameter tuning has been performed by researchers in the past to enhance the performance of classifiers. The AdaBoost algorithm belongs to a class of ensemble classifiers and is widely applied in binary classification problems. A single algorithm may not yield accurate results. However, an ensemble of classifiers built from multiple models has been successfully applied to solve many classification tasks. The search space to find an optimal set of parametric values is vast and so enumerating all possible combinations is not feasible. Hence, a hybrid modified whale optimization algorithm for spam profile detection (MWOA-SPD) model is proposed to find optimal values for these parameters. Design/methodology/approach In this work, the hyperparameters of AdaBoost are fine-tuned to find its application to identify spammers in social networks. AdaBoost algorithm linearly combines several weak classifiers to produce a stronger one. The proposed MWOA-SPD model hybridizes the whale optimization algorithm and salp swarm algorithm. Findings The technique is applied to a manually constructed Twitter data set. It is compared with the existing optimization and hyperparameter tuning methods. The results indicate that the proposed method outperforms the existing techniques in terms of accuracy and computational efficiency. Originality/value The proposed method reduces the server load by excluding complex features retaining only the lightweight features. It aids in identifying the spammers at an earlier stage thereby offering users a propitious environment.

TextSpamDetector: textual content based deep learning framework for social spam detection using conjoint attention mechanism

Online Social Networks (OSNs) allow easy membership leading to registration of a huge population and generation of voluminous information. These characteristics attract spammers to spread spam which may cause annoyance, financial loss, or personal information loss to the user and also weaken the reputation of social network sites. Most of the spam detection methods are based on user and content-based features using machine learning techniques. But, these annotated features are difficult to extract in real-time due to the privacy policy of most social network sites. Even for the features that can be extracted, because of their large size, the manual extraction process is complex and time-consuming. So there is a need for text level spam detection that does not require extraction of hard-core features. Existing deep learning based or existing single attention mechanism based text classification methods could not perform well as social network data are sparse with short texts and noises. Moreover, Spammers avoid direct spam words and use indirect words to evade spam filtering techniques and thus resulting in the dynamic and non-stationary nature of the social network spam texts. These indirect words contain hidden context that creates attention drift problem. So conjoint attention mechanism along with two attention mechanisms namely normal attention and context preserving attention are proposed to avoid attention drift problem in this deep learning-based text level spam detection technique (TextSpamDetector). Attention drift problem is solved by one attention mechanism which helps to find the important words while another attention mechanism allows focusing on attention in target context by referring to higher level abstraction of context vector. These attention mechanisms are referring to different context representations of the input text for finding informative words from the structural context representation. This structural context representation containing both local semantic features as well as global semantic dependency features is generated by CNN and BiLSTM. The proposed model is evaluated with the existing spam detection techniques using three datasets and the experimental results have proved that the proposed model performs well in terms of accuracy, F measure, and false-positive rate.

Attention-based approach of detecting spam in social networks

Attention-based approach of detecting spam in social networks

A Heterogeneous Ensemble Learning Framework for Spam Detection in Social Networks with Imbalanced Data

The popularity of social networks provides people with many conveniences, but their rapid growth has also attracted many attackers. In recent years, the malicious behavior of social network spammers has seriously threatened the information security of ordinary users. To reduce this threat, many researchers have mined the behavior characteristics of spammers and have obtained good results by applying machine learning algorithms to identify spammers in social networks. However, most of these studies overlook class imbalance situations that exist in real world data. In this paper, we propose a heterogeneous stacking-based ensemble learning framework to ameliorate the impact of class imbalance on spam detection in social networks. The proposed framework consists of two main components, a base module and a combining module. In the base module, we adopt six different base classifiers and utilize this classifier diversity to construct new ensemble input members. In the combination module, we introduce cost sensitive learning into deep neural network training. By setting different costs for misclassification and dynamically adjusting the weights of the prediction results of the base classifiers, we can integrate the input members and aggregate the classification results. The experimental results show that our framework effectively improves the spam detection rate on imbalanced datasets.

Detection of Social Network Spam Based on Improved Extreme Learning Machine

With the rapid advancement of the online social network, social media like Twitter has been increasingly critical to real life and become the prime objective of spammers. Twitter spam detection refers to a complex task for the involvement of a range of characteristics, and spam and non-spam have caused unbalanced data distribution in Twitter. To solve the mentioned problems, Twitter spam characteristics are analyzed as the user attribute, content, activity and relationship in this study, and a novel spam detection algorithm is designed based on regularized extreme learning machine, called the Improved Incremental Fuzzy-kernel-regularized Extreme Learning Machine (I2FELM), which is used to detect the Twitter spam accurately. As revealed from the experience validation results, the proposed I2FELM can efficiently identify the balanced and unbalanced dataset. Moreover, with few characteristics taken, the I2FELM can more effectively detect spam, which proves the effectiveness of the algorithm.

GAMEFEST: Genetic Algorithmic Multi Evaluation measure based FEature Selection Technique for social network spam detection

Social Network sites have become incredibly important in the present day. This popularity attracts the attacker to easily approach a large population and to have access to massive information for performing intrusion activities in Online Social Networks (OSN) including spamming. Spammers not only spread unsolicited messages but also perform malicious activities that harm the user’s financial or personal life and tarnish the reputation of social network platforms. Efficient spam detection requires the selection of relevant features to portray spammer behavior. Most of the existing feature selection techniques use any one of the evaluation measures such as, distance, dependence, consistency, information, and classifier error rate. The feature selection techniques select features from different perspectives based on the evaluation measures. Each evaluation measure produces different subset, and the detection rate differs accordingly. The majority of the existing works focus on the individual feature ranking, and discard the lowest weight feature. Lowest weight feature may produce more accurate prediction if, it is combined with other features. So, there is a need for the feature selection technique that considers the characteristics of all the evaluation measures to produce the appropriate subset, which increases the spam detection rate and assigns a weight for the combination of features. In regard to this, the paper proposes a new multi evaluation measure combined with feature subset selection based on the genetic algorithm, GAMEFEST. The performance of the proposed work has been evaluated using Twitter, Apontador, and YouTube datasets. Experimental results prove that our proposed GAMEFEST with Minimum Surplus Crossover (MSC) improves the efficiency of the learning process and increases the spam detection rate.

Predicting Rogue Content and Arabic Spammers on Twitter

Twitter is one of the most popular online social networks for spreading propaganda and words in the Arab region. Spammers are now creating rogue accounts to distribute adult content through Arabic tweets that Arabic norms and cultures prohibit. Arab governments are facing a huge challenge in the detection of these accounts. Researchers have extensively studied English spam on online social networks, while to date, social network spam in other languages has been completely ignored. In our previous study, we estimated that rogue and spam content accounted for approximately three quarters of all content with Arabic trending hashtags in Saudi Arabia. This alarming rate, supported by autonomous concurrent estimates, highlights the urgent need to develop adaptive spam detection methods. In this work, we collected a pure data set from spam accounts producing Arabic tweets. We applied lightweight feature engineering based on rogue content and user profiles. The 47 generated features were analyzed, and the best features were selected. Our performance results show that the random forest classification algorithm with 16 features performs best, with accuracy rates greater than 90%.

Spam detection on social networks using cost-sensitive feature selection and ensemble-based regularized deep neural networks

Spam detection on social networks is increasingly important owing to the rapid growth of social network user base. Sophisticated spam filters must be developed to deal with this complex problem. Traditional machine learning approaches such as neural networks, support vector machines and Naïve Bayes classifiers are not effective enough to process and utilize complex features present in high-dimensional data on social network spam. Moreover, the traditional objective criteria of social network spam filters cannot cope with different costs assigned to type I and type II errors. To overcome these problems, here we propose a novel cost-sensitive approach to social network spam filtering. The proposed approach is composed of two stages. In the first stage, multi-objective evolutionary feature selection is used to minimize both the misclassification cost of the proposed model and the number of attributes necessary for spam filtering. Then, the approach uses cost-sensitive ensemble learning techniques with regularized deep neural networks as base learners. We demonstrate that this approach is effective for social network spam filtering on two benchmark datasets. We also show that the proposed approach outperforms other popular algorithms used in social network spam filtering, such as random forest, Naïve Bayes or support vector machines.

Analysis of and defense against crowd-retweeting based spam in social networks

Social networking websites with microblogging functionality, such as Twitter or Sina Weibo, have emerged as popular platforms for discovering real-time information on the Web. Like most Internet services, these websites have become the targets of spam campaigns, which contaminate Web contents and damage user experiences. Spam campaigns have become a great threat to social network services. In this paper, we investigate crowd-retweeting spam in Sina Weibo, the counterpart of Twitter in China. We carefully analyze the characteristics of crowd-retweeting spammers in terms of their profile features, social relationships and retweeting behaviors. We find that although these spammers are likely to connect more closely than legitimate users, the underlying social connections of crowd-retweeting campaigns are different from those of other existing spam campaigns because of the unique features of retweets that are spread in a cascade. Based on these findings, we propose retweeting-aware link-based ranking algorithms to infer more suspicious accounts by using identified spammers as seeds. Our evaluation results show that our algorithms are more effective than other link-based strategies.

Detecting spams in social networks using ML algorithms - a review

The social network, by the name which has popularised in today's world and growing rapidly at all times and controlling over mankind. The social networks like Twitter, Facebook, and LinkedIn, etc., have become a regular and daily usage of many people. It becomes a good mediator for the people who would like to share some posts, are some of their own videos, or some messages. But there has been major issues that the particular user of the social networks like Twitter and Facebook have the problem of indiscipline actions which we call as spam, by the third person who is knowingly doing this to spoil their intention and good opinion upon each other. Also, these spams help to steal information about the people who using social networks. In this paper, we study and analyse about the spam in social networks and machine learning algorithms to detect such kind of spams. This paper also focuses on the ML algorithms detection rate and false positive rate over different datasets.

Efficient Classifier for Detecting Spam in Social Networks through Sentiment Analysis

Reaching hundreds million of users, major social networks have become important target media for spammers. Social networks provide communication between people to share information through internet. The unbounded growth of content and users pushes the Internet technologies usage to certain limitations. To extract relevant content from the voluminous data in social network which is being a phenomenal task, because of its dynamic nature the participation is more complex than the static database. This work concentrates on using sentiment analysis and applying efficient classifier to detecting the spammer actions. The main objective of the proposed work is to analyze the sentiment differences between spammers and normal users to detect spam message from the unwanted sites. Further discuss the relationship between sentiment score and spam reviews establish an instant sequence combined with discriminative rules to detect spam store and spam review efficiently. The system applies efficient classification algorithms for detecting spam in better way after sentiment analysis. Experimental results on social media datasets show the advanced performance of the proposed framework by sentiment analysis of social spammer detection with cost effective manner.