Paper Info
Title
Classification of Web Site by Naive-Bayes and Convolutional Neural Networks
Abstract
An approach for automatic classification and evaluation method for the structures of public World Wide Web sites by Naive-Bayes and Two-layer Convolutional Neural Networks is proposed in this paper. The proposed method is also worthy for analyzing contents and hypertext structures for commercial, education and nonprofit organizations. The aim of this proposal is to be available to use Internet safely and conveniently for users who do not have expert knowledge. In this paper, we explain the method for creating and evaluating models, and define the most relevant attributes to this process. We also implemented the method as a system for classifying web sites. The introduced software tool supports the automated collection of parameters of web sites, and it assures the necessary critical mass of empirical data. With the pre-processed information, statistical clustering (SOM and K-Means), text classification (Naive-Bayes), and Two-layer Convolutional Neural Networks are evaluated in this paper.
Year
DOI
Venue
2018
10.1145/3164541.3164581
IMCOM
Keywords
Field
DocType
Web Site Structure, HyperText Markup Language, Comparative Analysis, Self-Organizing Maps, Naive-Bayes, Convolutional Neural Network, Classification
Hypertext,Naive Bayes classifier,Computer science,Convolutional neural network,Computer network,Self-organizing map,Artificial intelligence,Cluster analysis,HTML,Machine learning,Web site,The Internet
Conference
ISBN
Citations 
PageRank 
978-1-4503-6385-3
0
0.34
References 
Authors
4
2
Name
Order
Citations
PageRank
Xueyan Liu1186.36
Ryuya Uda26321.76