Intelligent Data Analytics for Terror Threat Prediction. Группа авторов

Intelligent Data Analytics for Terror Threat Prediction - Группа авторов


Скачать книгу
classifies as large margin in between two types of data: first one is in circle shape and the second one is in triangle shape. These two data points have been classified with maximum distance (thick line) between them. The large margin shown in Figure 1.5(a) says that it is classifying those circles and triangles equally from that point, which means distance between those two data types is maximum through that margin. As shown in Figure 1.5(b), SVM also supports multi-dimensional data.

Schematic illustration of Hyperplane in two-dimension and three-dimension.

      1.4.1.2.1 Cost Function and Gradient Features

      SVM algorithm looks to maximize the margin between the data points and the hyper plane. The loss function that helps maximize the margin is hinge loss [8] and is defined as follows:

      (1.2) image

      If predicted value and expected value have the same sign then the cost function is 0.

      1.4.2 Combating Misinformation on Instagram

      Classification of shared contents by users in social media is prevalent in combating misinformation. Baseline classification algorithms like Naïve Bayes theorem and SVM models have been used extensively for detecting rumor as discussed Section 1.4. Even though these algorithms classify rumors and facts in some manner, still there is a need to come up with some excellent techniques which may improve efficiency in rumor classification. Nowadays, social networks like Facebook, WhatsApp, Instagram and Twitter are using good techniques, but still they failed to classify the rumors exactly.

      One of the popular social network, Facebook, has started in Instagram application (in US) to detect whether given post contains fact-information or false-information through some third party called as fact-checkers [33]. These third-party-fact-checkers are located globally and find rate of fact and false about particular post. When something is wrong in any post immediately fact-checkers check ratio of fact or misinformation.

Schematic illustration of Combating misinformation in Instagram.

      Rumor detection is not only a solution to prevent these cyber-crimes in social media, but finding source plays an important role to prevent further diffusion and punish the culprit. Initially, finding source of rumors in network discussed by Ref. [9]. Later, much research has been done and has introduced several factors which are to be considered in RS identification. There are mainly four factors considered namely, diffusion models, network structure, evaluation metrics, and centrality measures. Each factor has been explained in the following section with examples. After rumor detection, consider these factors and find rumor source using source detection methods in social networks are explained in Section 1.5.2.

      1.5.1 Network Structure

       1.5.1.1 Network Topology

      In computer networks, network topology is defined as design of physical and logical network. Physical design is the actual design of the computer cables and other network devices. The logical design is the way in which the network appears to the devices that use it.

      In complex networks, network topology is the arrangement of network in generic graph or tree. In general, many domains like medical, security, pipeline of water, gas, and power grid are available in graph structure. These graphs are required to restructure two topologies as d-regular trees and random geometric trees [34]. Initially, rumor source identification is discussed and introduces methods for general trees and general graphs based on rumor source estimator. Rumor source estimator plays a key role in finding the exact source of rumor. Source estimator mainly based on Maximum likelihood (ML) estimation is the same as a combinatorial problem [9, 35]. The following section will explain required techniques such as rumor source estimator, ML estimator, rumor centrality, and message passing algorithms to detect rumor source in trees.

      In rumor source identification, network structure plays an important role. When structure of network is known, it is easy to find how a rumor is spread in network using diffusion models such as SI, SIS, SIR and SIRS. If back track these diffusion models then rumor source can be detected easily. To know the structure of network another model is used called network observation, which provides information about states of each node present in network at particular time. Those states are in a susceptible node—able to being infected, infected node—that can widen the rumor more while recovered node—that is alleviates and no longer infected [10]. If information of each node likely is susceptible, infected or recovered is observed then it is easy to generate structure of network from that knowledge. Network observation can be done in three ways: complete observation, snapshot observation and monitor observation.

      1.5.1.2.1 Complete Observation


Скачать книгу