SFTM: Fast matching of web pages using Similarity-based Flexible Tree Matching

Tree matching techniques have been investigated in many fields, including web data mining and extraction, as a key component to analyze the content of pages. However, when applied existing pages, traditional tree approaches, covered by algorithms like Tree-Edit Distance (TED) or XyDiff, either fail scale beyond few hundred nodes exhibit relatively low accuracy. In this article, we therefore propose novel algorithm, named Similarity-based Flexible Matching (SFTM), which enables high accuracy on real-life with practical computation times. We approach an optimization problem leverage node labels local topology similarity order avoid any combinatorial explosion. Our evaluation demonstrates that SFTM significantly improves state art terms accuracy, while allowing times lower than most accurate solutions. By gaining these two dimensions, offers affordable solution match complex trees practice.