An Insight of Machine Learning in Web Network Analysis

An Insight of Machine Learning in Web Network Analysis

Meenakshi Sharma, Anshul Garg
Copyright: © 2019 |Pages: 15
DOI: 10.4018/IJDAI.2019070103
OnDemand:
(Individual Articles)
Available
$37.50
No Current Special Offers
TOTAL SAVINGS: $37.50

Abstract

The World Wide Web is immensely rich in knowledge. The knowledge comes from both the content and distinctive characteristics of the web like its hyperlink structure. The problem comes in digging the relevant data from the web and giving the most appropriate decision to solve the given problem, which can be used for improving any business organisation. The effective solution of the problem depends on how efficiently and effectively the analysis of the web data is done. In analysing the data on web, not only relevant content analysis is essential but also the analysis of web structure is important. This article gives a brief introduction about the various terminologies and measures like centrality, Page Rank, and density used in the web networking analysis. This article will also give a brief introduction about the various supervised ML techniques such as classification, regression, and unsupervised machine learning techniques such as clustering, etc., which are very useful in analysing the web network so that user can make quick and effective decision making
Article Preview
Top

2. Web Network

Network means interconnection of several objects. Web network is patterns in which different web objects are connected with each other. Web objects can be a commercial web site, web document, a web blog, a web document, etc. In web network analysis, the hyperlink structure and web document structure both are included. Web Network can be represented graphically with directed edges, undirected edges or weighted edges. The Figure 1 shows the graphical representation of web network

Figure 1.

Web network

IJDAI.2019070103.f01

Web network analysis is used to boost the web object’s performance. Web network can be shown theoretically by G={N, E} (Sagar et al., 2012).In this N is the total number of nodes and E is the total number of edges. In Figure 1 N={1, 2, 3, 4, 5, 6, 7}

2.1 Node

Another name for node is Vertex, Actor or Point. In web network node can be a web document, website, web service. When they are connected with direct edge they can be named as Neighbors (Sagar et al., 2012; Plazzl et al., 2012). If a node is connected with the group only by one connection, then is pendant node. The only node getting attention for analysis is the ego node and other node in the group are called alter node.

2.2 Edge

In Web Network, two actors are connected with each other with a connection, that connection is called Edge or Tie. Edge can be Weighted, Bounded and Directed. Two neighbor nodes can be strongly connected if there is edge from each node to each other (Plazzl et al., 2012) They are called weak connected if there is a path between them and edge orientation is not in consideration. In case of directed networking graph there are two types of link are there in-Link and Out-Link. The no of nodes pointing to that node are called in-links to that node and that node is pointing to

2.3 Path

The Path is the minimum actor in sequence to reach from one node to another. (Plazzl et al., 2012)

2.4 Diameter

It is the longest path available in web network.

2.5 Degree

Number of edges with which a node is connected. In case of directed it is the total of in-links and out links. The average of degree is the average of all degrees in network (Plazzl et al., 2012)

Complete Article List

Search this Journal:
Reset
Volume 15: 1 Issue (2024): Forthcoming, Available for Pre-Order
Volume 14: 2 Issues (2022)
Volume 13: 2 Issues (2021)
Volume 12: 2 Issues (2020)
Volume 11: 2 Issues (2019)
Volume 10: 2 Issues (2018)
View Complete Journal Contents Listing