A new classification approach based Support Vector Machine is proposed for detecting spammers on Twitter.The proposed approach reveals the most influencing features in the process of identifying spammers.Different lingual contexts are studied: Arabic, English, Spanish, and Korean. Detecting spam profiles is considered as one of the most challenging issues in online social networks. The reason is that these profiles are not just a source for unwanted or bad advertisements, but could be a serious threat; as they could initiate malicious activities against other users. Realizing this threat, there is an incremental need for accurate and efficient spam detection models for online social networks. In this paper, a hybrid machine learning model based on Support Vector Machines and one of the recent metaheuristic algorithms called Whale Optimization Algorithm is proposed for the task of identifying spammers in online social networks. The proposed model performs automatic detection of spammers and gives an insight on the most influencing features during the detection process. Moreover, the model is applied and tested on different lingual datasets, where four datasets are collected from Twitter in four languages: Arabic, English, Spanish, and Korean. The experiments and results show that the proposed model outperforms many other algorithms in terms of accuracy, and provides very challenging results in terms of precision, recall, f-measure and AUC. While it also helps in identifying the most influencing features in the detection process.

Evolving Support Vector Machines using Whale Optimization Algorithm for spam profiles detection on online social networks in different lingual contexts

The annotation of web sites in social bookmarking systems has become a popular way to manage and find information on the web. The community structure of such systems attracts spammers: recent post pages, popular pages or specific tag pages can be manipulated easily. As a result, searching or tracking recent posts does not deliver quality results annotated in the community, but rather unsolicited, often commercial, web sites. To retain the benefits of sharing one's web content, spam-fighting mechanisms that can face the flexible strategies of spammers need to be developed.A classical approach in machine learning is to determine relevant features that describe the system's users, train different classifiers with the selected features and choose the one with the most promising evaluation results. In this paper we will transfer this approach to a social bookmarking setting to identify spammers. We will present features considering the topological, semantic and profile-based information which people make public when using the system. The dataset used is a snapshot of the social bookmarking system BibSonomy and was built over the course of several months when cleaning the system from spam. Based on our features, we will learn a large set of different classification models and compare their performance. Our results represent the groundwork for a first application in BibSonomy and for the building of more elaborate spam detection mechanisms.

The Anti-Social Tagger - Detecting Spam in Social Bookmarking Systems.

Social media is rapidly becoming one of the mediums of choice for understanding the cultural pulse of a region; e.g., for identifying what the population is concerned with and what kind of help is needed in a crisis. To assess this cultural pulse it is critical to have an accurate assessment of who is saying what in social media. However, social media is also the home of malicious users engaged in disruptive, disingenuous, and potentially illegal activity. A range of users, both human and non-human, carry out such social cyber-attacks. We ask, to what extent does the presence or absence of such users influence our ability to assess the cultural pulse of a region? We conduct a series of experiments to analyze the fragility of social network assessments based on Twitter data by comparing changes in both the structural and content results when suspended users are left in and taken out. Because a Twitter account can be suspended for various reasons including spamming or spreading ideas that can lead to extremism or terrorism, we separately assess the impacts of removing apparent spam bots and apparent extremists. Experimental results demonstrate that Twitter-based network structures and content are unstable, and can be highly impacted by the removal of suspended users. Further, the results exhibit regional and temporal variation that may be related to the political situation or civil unrest. We also provides guidance on the differential impact of different types of potentially suspend-able users.

https://dl.acm.org/doi/pdf/10.1145/2808797.2809316

The Fragility of Twitter Social Networks Against Suspended Users

Social media is rapidly becoming a medium of choice for understanding the cultural pulse of a region; e.g. for identifying what the population is concerned with and what kind of help is needed in a crisis. To assess this cultural pulse, it is critical to have an accurate assessment of who is saying what. Unfortunately, social media is also the home of users who engage in disruptive, disingenuous, and potentially illegal activity. A range of users, both human and non-human, carry out such social cyber-attacks. We ask, to what extent does the presence or absence of such users influence our ability to assess the cultural pulse of a region? Our prior research on this topic showed that Twitter-based network structures and content are unstable and can be highly impacted by the removal of suspended users. Because of this, statistical techniques can be established to differentiate potential types of suspended and non-suspended users. In this extended paper, we develop additional experiments to explore the spatial patterns of suspended users, and we further consider how these users affect structural and content concentrations via the development of new metrics and new analyses. We find significant evidence that suspended users exist on the periphery of social networks on Twitter and consequently that removing them has little impact on network structure. We also improve prior attempts to distinguish among different types of suspended users by using a much larger dataset. Finally, we conduct a temporal sentiment analysis to illustrate differences between suspended users and non-suspended users on this dimension.

Exploring characteristics of suspended users and network stability on Twitter

Detecting online attacks is described, including identifying one or more events associated with users on a social graph. For each type of event of the one or more events, generating at least one directed acyclic graph (DAG), where each node on the DAG represents a node on the social graph where an event of the type occurs and each edge on the DAG represents a propagation of the event from a first node of the edge to a second node of the edge.

Systems and methods for detecting online attacks

As online social networks acquire a larger user base, they also become more interesting targets for spammers. Spam can take very different forms on social web sites and can not always be detected by analyzing textual content. However, the platform’s social nature also offers new ways of approaching the spam problem. In this work we analyze a user’s friends and followers to gain information on him. Next, we evaluate them using different metrics to determine the amount of trust his peers give him. We use the Twitter microblogging platform for this case study.

Can You Judge a Man by His Friends? - Enhancing Spammer Detection on the Twitter Microblogging Platform Using Friends and Followers

ENHANCING SPAMMER DETECTION IN ONLINE SOCIAL NETWORKS WITH TRUST-BASED METRICS by Alexander J. Murmann As online social networks acquire larger user bases, they also become more interesting targets for spammers. Spam can take very different forms on social Web sites and cannot always be detected by analyzing textual content. However, the platform's social nature also offers new ways of approaching the spam problem. In this work the possibilities of analyzing a user's direct neighbors in the social graph to improve spammer detection are explored. Special features of social Web sites and their implicit trust relations are utilized to create an enhanced attribute set that categorizes users on the Twitter microblogging platform as spammers or legitimate users.

/pdf/enhancing-spammer-detection-in-online-social-networks-with-5dflfjl56x.pdf

Enhancing spammer detection in online social networks with trust-based metrics.

We present first steps towards an architecture that enables autonomous systems to learn and adapt basic behaviors to unknown environments It can act as layer providing robust behaviors to higher-level layers like eg reinforcement learning or planning algorithms, that depend on encapsulated actions With emphasis on robustness it is able to learn to control its actors without any information about the meaning of its actors This is made possible by behavior modules that are learned together with their action-effect dependencies and their enabling preconditions by proactively carrying out experiments within their environment

Towards Robust Skill Learning With Prediction Guided Autonomy in Unknown Environments

To enable autonomous systems to learn basic skills for unknown and changing environments and stay robust in case of change, Organic Computing principles have to be applied at all layers. In this work an architecture is presented that can be used at the lowest layer providing robust skills to higher-level strategy layers, that depend on encapsulated actions. With emphasis on robustness it is able to learn to control its actors without a priori information about their meaning. This is made possible by skill modules that are learned together with their action-effect dependencies and their enabling preconditions by proactively carrying out experiments within their environment. The architecture is evaluated by simulating a differentially driven robot.

/pdf/self-organization-at-the-lowest-level-proactively-learning-3yjlsvnd0h.pdf

Alexander J. Murmann

Papers

Can You Judge a Man by His Friends? - Enhancing Spammer Detection on the Twitter Microblogging Platform Using Friends and Followers

Enhancing spammer detection in online social networks with trust-based metrics.

Towards Robust Skill Learning With Prediction Guided Autonomy in Unknown Environments

Self-organization at the lowest level: proactively learning skills in autonomous systems