Web content extraction based on subject detection and node density

• Published in: 2015 7th International Conference on Knowledge and Smart Technology (KST) pp. 121 - 125
• Main Authors: Petprasit, Warid, Jaiyen, Saichon
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.01.2015
• Subjects: Cascading style sheets; data intensive; Data mining; e-commerce; node density (SDND); subject detection; Uniform resource locators; web content extraction; web information extraction; web mining; Web pages; wrapper induction; XML
• DOI: 10.1109/KST.2015.7051455
• ISBN: 9781479960484; 1479960489

Currently, very large data have been transferred from everywhere through World Wide Web. Consequently, the information extraction systems have been arising and many researches have been focusing on those data for utilizing them. These systems are very useful for data pre-processing and cleaning for real-time applications. Moreover, these systems can make other analyzing systems to analyze the data in real time such as social network mining, web mining, data mining, or even special tasks such as false advertisement detection, demand forecasting, and comment extraction on product and service reviews. In this paper, we focus on extracting the content data of web pages in e-commerce web sites based on subject detection and node density. In the experimental results, it can signify that our proposed method is appropriated to extract the data rich region in data-intensive pages in an automatic fashion.