High quality facet generation by using a website wrapper
V K Vaishakhi, Neethu T Regi · 2017
The query facets are multiple groups of term or clause that justify and encapsulate the content covered by a query. When a query is given to the search engine, the lists are extracted from the search results. The lists are extracted using the list extraction algorithm. All extracted lists are given weights, unimportant or noisy lists that are encountered in a page are assigned by low weights. Similar lists are grouped into clusters using the weighted Quality Threshold Algorithm. Facets are then assessed and ranked. High rank is given for lists extracted from similar context and lists having higher weight. The problem addressed here to find the query facets and the navigation to the wanted web page. In order to increase the quality of the extracted list a website wrapper called Anchor based data extraction system is introduced. The facets are created based on the search interest of the user. The experiment is performed real time in Bing. From the created facets users can move to the wanted high ranking pages by selecting the item in the facets. This can be used to created facets in Bing.