Title identification of web article pages using HTML and visual features

Abstract

Extracting informative content from Web article pages has many applications such as printing and content reuse. Title is a very significant and unique component of an article. However, identifying the true title is not an easy problem even for human readers. In this paper, we present a title identification method that takes into account of several features including the title field of the HTML page and HTML tag of a DOM node as well as font size and horizontal alignment. We tested our method on a ground truth data set consisting of 1993 pages from 98 web sites and achieved 97.5% accuracy, about 20% above a baseline method based on only the font size.

Page query language generation for structural extraction

“…[18] gives a survey of web information extraction systems. [1,2,3] have studied main article extraction on the Web; [4] focuses on the identification of titles in web pages, [5] investigates authors extraction of web document. Earlier, [6] has proposed a rule learning algorithm LP2, and implemented an automatic structural extraction module used by some semantic structural extraction systems [9].…”

“…Extracting structural informative content from web pages has attracted many re-search efforts in recent years [1,2,3,4,5]. The identification and extraction of the main article [1,2,3], paper title [4] and authors [5] is studied in the literature.…”

“…The identification and extraction of the main article [1,2,3], paper title [4] and authors [5] is studied in the literature. In this paper, we focus on extracting general structural groups from data-intensive web pages with PQL (Page Query Language), a SQL like query language.…”

Semi-Automatic Online Tagging with K-Medoid Clustering

“…Tagging and extracting informative content from web pages has attracted many research e®orts in recent years [1][2][3][4][5]. The identi¯cation of titles [4], authors [5], and the main article [1][2][3] is studied in the literature.…”

“…The identi¯cation of titles [4], authors [5], and the main article [1][2][3] is studied in the literature. In this paper, we focus on identifying general semantic groups from data-intensive web pages with a hybrid approach which combines user guidance and unsupervised clustering techniques.…”