Social Spam Research Articles

A Comprehensive Survey on Graph Anomaly Detection With Deep Learning

Anomalies represent rare observations (e.g., data records or events) that deviate significantly from others. Over several decades, research on anomaly mining has received increasing interests due to the implications of these occurrences in a wide range of disciplines. Anomaly detection, which aims to identify rare observations, is among the most vital tasks in the world, and has shown its power in preventing detrimental events, such as financial fraud, network intrusion, and social spam. The detection task is typically solved by identifying outlying data points in the feature space and inherently overlooks the relational information in real-world data. Graphs have been prevalently used to represent the structural information, which raises the graph anomaly detection problem - identifying anomalous graph objects (i.e., nodes, edges and sub-graphs) in a single graph, or anomalous graphs in a database/set of graphs. However, conventional anomaly detection techniques cannot tackle this problem well because of the complexity of graph data. For the advent of deep learning, graph anomaly detection with deep learning has received a growing attention recently. In this survey, we aim to provide a systematic and comprehensive review of the contemporary deep learning techniques for graph anomaly detection. We compile open-sourced implementations, public datasets, and commonly-used evaluation metrics to provide affluent resources for future studies. More importantly, we highlight twelve extensive future research directions according to our survey results covering unsolved and emerging research problems and real-world applications. With this survey, our goal is to create a "one-stop-shop" that provides a unified understanding of the problem categories and existing approaches, publicly available hands-on resources, and high-impact open challenges for graph anomaly detection using deep learning.

Spam community detection & influence minimization using NRIM algorithm

Big Data is a research area where many different disciplines work together. Social media has grown in popularity as a tool for disseminating and gathering information. However, the success of social media like Twitter, Facebook, etc., has not only attracted genuine users but also spammers who utilize social graphs, famous phrases, and hashtags to spread malware. This study uses several social network analysis and visualization methods based on bibliometric data from the Web of Science to look at the structure and patterns of interdisciplinary collaborations and the latest emerging overall practice. For a better understanding of spamming behaviors on Twitter, the Twitter data set is thoroughly analyzed, and categorized into Spam and Non-Spam classifications. Earlier studies confined their scope to investigating the most negatively influential spammers by blocking the most influential spammers. However, the cumulative impact of other spammers having low individual negative influence values but higher impact values was neglected. In this article, we develop an algorithm for detecting social spam using Node Rank-based Influence Minimization (NRIM), which integrates Node Rank with the impact value of spam. The proposed spam influence minimization model also identifies spam-influential users and aids in limiting the flow of spam tweets within the Twitter network. Additionally, a detection algorithm for influential communities has been proposed to limit the spread of spam content through influential communities on the Twitter network. The primary focus of this paper is to reduce the spam impact on Twitter data by identifying influential spammers using the Node_Rank-based Influence Minimization (NRIM) algorithm. To begin, the tweets are classified into spam and non-spam using a machine learning algorithm. Furthermore, the spam observed in the Graph is analyzed, and the Spammer is passed through the NRIM algorithm to find the influential Spammers. In addition to this, the negative impact of the Spammer is reduced on the Twitter graph, and its impact is analyzed on query processing executed on Graph. The technique used for the minimization of the Spammer’s negative effect on the graph reduces the query execution time by 12%.

DSpamOnto: An Ontology Modelling for Domain-Specific Social Spammers in Microblogging

The lack of regulations and oversight on Online Social Networks (OSNs) has resulted in the rise of social spam, which is the dissemination of unsolicited and low-quality content that aims to deceive and manipulate users. Social spam can cause a range of negative consequences for individuals and businesses, such as the spread of malware, phishing scams, and reputational damage. While machine learning techniques can be used to detect social spammers by analysing patterns in data, they have limitations such as the potential for false positives and false negatives. In contrast, ontologies allow for the explicit modelling and representation of domain knowledge, which can be used to create a set of rules for identifying social spammers. However, the literature exposes a deficiency of ontologies that conceptualize domain-based social spam. This paper aims to address this gap by designing a domain-specific ontology called DSpamOnto to detect social spammers in microblogging that targes a specific domain. DSpamOnto can identify social spammers based on their domain-specific behaviour, such as posting repetitive or irrelevant content and using misleading information. The proposed model is compared and benchmarked against well-proven ML models using various evaluation metrics to verify and validate its utility in capturing social spammers.

Hybrid ensemble framework with self-attention mechanism for social spam detection on imbalanced data

Cybercriminals use social media platforms to disseminate spam, misleading facts, fake news, and malicious links. Blocking such deceptive social media spam is essential. However, extracting relevant features from social networks is challenging due to privacy and time constraints. Traditional frequency-based word representation techniques are time-consuming and inefficient in producing contextual word vectors. Word embeddings and deep learning models have recently shown good results in text classification. Also, most existing approaches assumed balanced class distribution, which is false for most real-world datasets. In this paper, an attempt is made to advance the performance of the social spam detection system by leveraging dataset balancing, advanced word embedding techniques, machine learning, and deep learning approaches with the self-attention mechanism. In the proposed framework, the datasets are balanced using NearMiss and SmoteTomek techniques to feed several machine-learning models. Later, the baseline ML models and proposed voting-based ensemble models are evaluated on imbalanced and balanced datasets. For the proposed deep learning-based hybrid approaches, embeddings are generated using GloVe and FastText word embeddings on the balanced combined dataset and passed into the deep neural network comprised of Conv1D and Bi-directional recurrent neural network layers with the self-attention mechanism for improved context understanding and effective results. This study examines hybrid approaches for detecting social spam using imbalanced social network data and picks the optimum combination. Besides, Machine learning ensembles, word embeddings, deep learning with hyper-parameter optimization, and a self-attention method are compared thoroughly. Experiments and comparisons with other techniques show that the proposed hybrid framework with deep learning-based approaches achieves better performance.

Achieving Online and Scalable Information Integrity by Harnessing Social Spam Correlations

Malicious web links, social rumors, fraudulent advertisements, faked comments, and biased propaganda are overwhelmingly influencing online social networks. Enabling information integrity is a hot topic in both academia and industry. Traditional social spam detection techniques rely on centralized processing, focusing only on one specific set of data sources, thereby ignoring the social spam correlations between distributed data sources. In this paper, we propose an online and scalable misinformation detection system, named Spiral, to uncover social spam by leveraging the correlations between different social data sources in geo-distributed sites. The key insight in our approach is to amplify the effectiveness of state-of-the-art techniques to detect inappropriate posts by enabling the efficient large-scale propagation of detection information across domains. The novelty of our design lies in three key components: (1) a decentralized distributed hash-table-based tree overlay deployment for harvesting and uncovering deceptive information spreading in multiple online social networks communities; (2) a progressive aggregation tree for collecting the properties of these posts and creating new classifiers to actively filter out the propagation of inappropriate posts; and (3) a group communication structure that allows multiple groups to exchange the correlations among distributed social data sources. We designed and implemented a prototype of the Spiral system. Our large-scale experiments, using real-world social data, demonstrate Spiral’s scalability, effective load-balancing, and efficiency in online spam detection for social networks.

Enhancing Detection of Arabic Social Spam Using Data Augmentation and Machine Learning

In recent years, people have tended to use online social platforms, such as Twitter and Facebook, to communicate with families and friends, read the latest news, and discuss social issues. As a result, spam content can easily spread across them. Spam detection is considered one of the important tasks in text analysis. Previous spam detection research focused on English content, with less attention to other languages, such as Arabic, where labeled data are often hard to obtain. In this paper, an integrated framework for Twitter spam detection is proposed to overcome this problem. This framework integrates data augmentation, natural language processing, and supervised machine learning algorithms to overcome the problems of detection of Arabic spam on the Twitter platform. The word embedding technique is employed to augment the data using pre-trained word embedding vectors. Different machine learning techniques were applied, such as SVM, Naive Bayes, and Logistic Regression for spam detection. To prove the effectiveness of this model, a real-life data set for Arabic tweets have been collected and labeled. The results show that an overall improvement in the use of data augmentation increased the macro F1 score from 58% to 89%, with an overall accuracy of 92%, which outperform the current state of the art.

SOCIAL MEDIA SPAM DETECTION USING DIFFERENT TEXT FEATURE SELECTION TECHNIQUE AND MACHINE LEARNING

The messaging systems and social media is popular and has essential contributions to our social and professional life. Similarly, Spam is a part of the messaging system and social media. In social media, spam is found in various places (i.e. in posts, in comments, in reviews, and in chatting). Social media Spam is aimed to influence the user’s decision, point of view, and credibility of the service or brand. Therefore, social spam detection is essential. However, using the social media data a number of contributions are available in literature, but a fewer amount of work is available for social media spam detection. In this paper, we proposed a social media spam detection technique using machine learning and text feature extraction techniques. In this context first, a review on social media spam detection techniques has been carried out. Using this review, we extract the different machine learning techniques used, techniques of text feature selection, and experimental datasets used. In this review, we found that the spam messages with the URLs are more critical and harmful. Next step, we design a theoretical model for social media spam detection, which includes text feature selection techniques (i.e. TF-IDF, POS, and Information Gain) and their combinations (POS+TF-IDF and POS+IG). These features are used with Support Vector Machine (SVM), Artificial Neural Network, and Naïve Bayes classifier for training. Experimental analysis with dataset available in Kaggle we found that hybrid features is more effective for accurate classification as compared to individual features. Additionally, we found for classification the SVM and ANN are more accurate as compared to the Bayes classifier.

An intelligent system for multi-topic social spam detection in microblogging

The communication revolution has perpetually reshaped the means through which people send and receive information. Social media is an important pillar of this revolution and has brought profound changes to various aspects of our lives. However, the open environment and popularity of these platforms inaugurate windows of opportunities for various cyber threats, thus social networks have become a fertile venue for spammers and other illegitimate users to execute their malicious activities. These activities include phishing hot and trendy topics and posting a wide range of contents in many topics. Hence, it is crucial to continuously introduce new techniques and approaches to detect and stop this category of users. This article proposes a novel and effective approach to detect social spammers. An investigation into several attributes to measure topic-dependent and topic-independent users’ behaviours on Twitter is carried out. The experiments of this study are undertaken on various machine learning classifiers. The performance of these classifiers is compared and their effectiveness is measured via a number of robust evaluation measures. Furthermore, the proposed approach is benchmarked against state-of-the-art social spam and anomalous detection techniques. These experiments report the effectiveness and utility of the proposed approach and embedded modules.

A Data Mining Approach for Filtering out Social Spammers in Large-Scale Twitter Data Collections

Social networking services – such as Facebook.com and Twitter.com – are fast-growing enterprise platform that has become a prevalent and essential component of daily life. Due to its popularity, Twitter draws many spammers or other fake accounts to post malicious links and infiltrate legitimate users' accounts with many spam messages. Therefore, it is crucial to recognize and screen spam tweets and spam accounts. As a result, spam detection is highly needed but still a difficult challenge. This article applied several Bio-inspired optimization algorithms to reduce the features' dimensions in the first stage. Then we used several classification schemes in the second stage to enhance the spam detection rate in three real Twitter data collections. The performance of the chosen classifiers also revealed that Random Forest and C4.5 classifiers achieved the highest Accuracy, Precision, Recall, and F1-score even on class imbalance.

Boosting Social Spam Detection via Attention Mechanisms on Twitter

Twitter is one of the largest social networking platforms, which allows users to make friends, read the latest news, share personal ideas, and discuss social issues. The huge popularity of Twitter mean it attracts a lot of online spammers. Traditional spam detection approaches have shown the effectiveness for identifying Twitter spammers by extracting handcrafted features and training machine learning models. However, such models need knowledge from domain experts. Moreover, the behaviors of spammers can change according to the defense strategies of Twitter. These result in the ineffectiveness of the traditional feature-based approaches. Although deep-learning-based approaches have been proposed for detecting Twitter spammers, they all treat each tweet equally, and ignore the differences among them. To solve these issues, in this paper, we propose a new attention-based deep learning model to detect social spammers in Twitter. In particular, we first introduce the state-of-the-art pretraining model BERTweet for learning the representation of each tweet, and then use the proposed novel attention-based mechanism to learn the user representations by distinguishing the differences among tweets posted by each user. Moreover, we take social interactions into consideration and propose that a graph attention network is used to update the learned user representations, to further improve the accuracy of identifying spammers. Experiments on a publicly available, real-world Twitter dataset show the effectiveness of the proposed model, which is able to significantly enhance the performance.

Spam Detection on Summarized Graph

As the popularity of social networking sites continues to increase, spam accounts are also on the rise. Over the past few years, social networking and information-sharing microblogging websites such as Twitter and Sina Weibo have gained popularity. Unsolicited content, such as social spam, has also been exploited by spammers to overwhelm most users unfairly. In contrast to existing work, this paper uses a novel graph-based approach for spam detection. The problem of graph summarization has practical applications involving visualization and graph compression. As graph-structured databases become popular and prominent, summarizing and compressing graph-structured databases can become more and more valuable. Our experimental results demonstrate the usefulness and efficiency of our proposed strategy. The accuracy of the graph is considered before and after Graph Summarization using MultiNominal NB and then compared with other machine learning algorithms. Various algorithms are considered, and it is found that MultiNominal NB gives the lowest training time and the highest accuracy. The training time of MultiNominal NB is found to be 0.55 sec before graph summarization. After graph summarization, the training time is optimized to be 0.02 seconds, and the accuracy value is 96.64%.

Social Spammer Detection via Convex Nonnegative Matrix Factorization

With the increasing popularity of social network platforms such as Twitter and Sina Weibo, a lot of malicious users, also known as social spammers, disseminate illegal information to normal users. Several approaches are proposed to detect spammers by training a classifier with optimization methods and mainly using content and social following information. Due to the development of spammers’ strategies and the courtesy of some legitimate users, social following information becomes vulnerable to fake by spammers. Meanwhile, the possible social activities and behaviors vary significantly among different users, which leads to a large yet sparse feature space to be modeled by existing approaches. To address issues, in this paper, we propose a new approach named CNMFSD for spammer detection in social networks, which exploits both content information and users interaction relationships in an innovative manner. We have empirically validated the proposed method on a real-world Twitter dataset, and experimental results show that the proposed CNMFSD method improves the detection performance significantly compared with baselines.

Heterogeneous Ensemble with Combined Dimensionality Reduction for Social Spam Detection

This study presents a novel framework based on a heterogeneous ensemble method and a hybrid dimensionality reduction technique for spam detection in micro-blogging social networks. A hybrid of Information Gain (IG) and Principal Component Analysis (PCA) (dimensionality reduction) was implemented for the selection of important features and a heterogeneous ensemble consisting of Naïve Bayes (NB), K Nearest Neighbor (KNN), Logistic Regression (LR) and Repeated Incremental Pruning to Produce Error Reduction (RIPPER) classifiers based on Average of Probabilities (AOP) was used for spam detection. The proposed framework was applied on MPI_SWS and SAC’13 Tip spam datasets and the developed models were evaluated based on accuracy, precision, recall, f-measure, and area under the curve (AUC). From the experimental results, the proposed framework (that is, Ensemble + IG + PCA) outperformed other experimented methods on studied spam datasets. Specifically, the proposed method had an average accuracy value of 87.5%, an average precision score of 0.877, an average recall value of 0.845, an average F-measure value of 0.872 and an average AUC value of 0.943. Also, the proposed method had better performance than some existing methods. Consequently, this study has shown that addressing high dimensionality in spam datasets, in this case, a hybrid of IG and PCA with a heterogeneous ensemble method can produce a more effective method for detecting spam contents.

ACTSSD: social spammer detection based on active learning and co-training

ACTSSD: social spammer detection based on active learning and co-training

Detecting Nuisance Calls over Internet Telephony Using Caller Reputation

Internet telephony permit callers to manage self-asserted profiles without any subscription contract nor identification proof. These cost-free services have attracted many telemarketers and spammers who generate unsolicited nuisance calls. Upon detection, they simply rejoin the network with a new identity to continue their malicious activities. Nuisance calls are highly disruptive when compared to email and social spam. They not only include annoying telemarketing calls but also contain scam and voice phishing which involves security risk for subscribers. Therefore, it remains a major challenge for Internet telephony providers to detect and avoid nuisance calls efficiently. In this paper, we present a new approach that uses caller reputation to detect different kinds of nuisance calls generated in the network. The reputation is computed in a hybrid manner by extracting information from call data records and using recommendations from reliable communicating participants. The behavior of the caller is assessed by extracting call features such as call-rate, call duration, and call density. Long term and short term reputations are computed to quickly detect the changing behavior of callers. Furthermore, our approach involves an efficient mechanism to combat whitewashing attacks performed by malicious callers to continue generating nuisance calls in the network. We conduct simulations to compute the performance of our proposed model. The experiments conclude that the proposed reputation model is an effective method to detect different types of nuisance calls while avoiding false detection of legitimate calls.

An Adaptive Social Spammer Detection Model With Semi-Supervised Broad Learning

Mobile social networks include a large number of social members who forward messages cooperatively. However, spammers post links to viruses and advertisements, or follow a large number of users, which produces many misleading messages in mobile social networks. In this paper, we propose an adaptive social spammer detection (ASSD) model. We build a spammer classifier by using a small number of labeled patterns and some unlabeled patterns. The prediction accuracy is high compared with some conventional supervised learning methods. Moreover, the time and energy required to label the identity of social members are reduced by applying ASSD. Because social spammers frequently change their behavior to deceive the spammer detection model, an incremental learning method is designed to update the spammer detection model adaptively, without retraining. We evaluate ASSD by comparing it with other supervised and semi-supervised machine learning methods using the Social Honeypot Dataset. Experimental results show that the proposed model outperforms the baseline methods in terms of recall and precision. Additionally, ASSD maintains a high detection accuracy by adaptively updating the model with newly generated social media data.

Particle Swarm Optimization on Deep Reinforcement Learning for Detecting Social Spam Bots and Spam-Influential Users in Twitter Network

In online social networks (OSNs), detection of malicious social bots is an important research challenge to provide legitimacy of user profiles and trustworthy service ratings. Further, spam-influential users must be minimal to control the fake information-spread in OSNs. Learning from example patterns using supervised learning may not provide accurate results in cases where existing data items are biased and bot behavior dynamically changes over a period of time. Moreover, deep reinforcement learning provides improved learning by repeated interactions with the environment. However, a typical deep reinforcement leaning algorithm converges slower to find an optimal sequence of actions to reach out a goal state. In this article, we design a particle swarm optimization (PSO) based deep Q-learning algorithm for detecting social spam bots by integrating PSO with Q-value function. In addition, spam-influential users are identified using the proposed spam influence minimization model and it helps in restricting the flow of illegitimate tweets in Twitter network. Further, an influential community detection algorithm has been proposed to reduce the spreading of spam content through influential communities in Twitter network. Experimental results illustrate the efficacy of our proposed algorithms by considering two Twitter datasets and performance metrics such as precision, recall, and modularity.

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.

Leveraging multi-level dependency of relational sequences for social spammer detection

Much recent research has shed light on developing the relation-dependent but the content-independent framework for social spammer detection. This is mainly because the relation among users is difficult to be altered when spammers attempt to conceal their malicious intentions. Our study investigates the spammer detection problem in the context of multi-relation social networks and makes an attempt to fully exploit the sequences of heterogeneous relations for enhancing the detection accuracy. Specifically, we present the Multi-level Dependency Model (MDM). The MDM is able to exploit the user’s long-term dependency hidden in their relational sequences along with short-term dependency. Moreover, MDM fully considers short-term relational sequences from the perspectives of individual-level and union-level, due to the fact that the type of short-term sequences is multi-folds. Experimental results on a real-world multi-relational social network demonstrate the effectiveness of our proposed MDM on multi-relational social spammer detection.

Spam and Fake Spam Message Detection Framework Using Machine Learning Algorithm

Online reviews about the acquisition of items or administrations gave have become the primary wellspring of clients’ conclusions. So as to pick up benefit or acclaim, as a rule spam reviews are composed to advance or downgrade a couple of target items or administrations. This training is known as review spamming. In the previous barely any years, an assortment of strategies have been proposed so as to illuminate the issue of spam reviews. It is a mainstream correspondence and furthermore known as information trade media. Information could be of a book, numbers, figures or insights that are gotten to by a PC. These days, numerous individuals relies upon substance accessible in web-based social networking in their choices. Sharing of data with people groups has additionally pulled in social spammers to endeavor and spread spam messages to advance individual web logs, notices, advancements, phishing, trick, fakes, etc. The possibility that anyone will leave a review give a brilliant possibility for spammers to post spit audit with respect to item and administrations for different interests and possibilities. In this way, we propose a fake message detection system utilizing ML to recognize the spam and fake messages on the internet based life stage.