Pattern discovery for semi-structured web pages using bar-tree representation

TL;DR

This paper introduces the bar-tree representation for pattern discovery in semi-structured web pages, enabling efficient recognition of template changes and improving data extraction accuracy.

Contribution

The novel bar-tree representation and reverse algorithm improve pattern recognition and change detection in semi-structured web pages compared to previous methods.

Findings

High recognition rate for template changes

Efficient pattern description using bar graphs

Effective detection of pattern modifications

Abstract

Many websites with an underlying database containing structured data provide the richest and most dense source of information relevant for topical data integration. The real data integration requires sustainable and reliable pattern discovery to enable accurate content retrieval and to recognize pattern changes from time to time; yet, extracting the structured data from web documents is still lacking from its accuracy. This paper proposes the bar-tree representation to describe the whole pattern of web pages in an efficient way based on the reverse algorithm. While previous algorithms always trace the pattern and extract the region of interest from \textit{top root}, the reverse algorithm recognizes the pattern from the region of interest to both top and bottom roots simultaneously. The attributes are then extracted and labeled reversely from the region of interest of targeted contents. Since using conventional representations for the algorithm should require more computational power, the bar-tree method is developed to represent the generated patterns using bar graphs characterized by the depths and widths from the document roots. We show that this representation is suitable for extracting the data from the semi-structured web sources, and for detecting the template changes of targeted pages. The experimental results show perfect recognition rate for template changes in several web targets.