Query Intent Determination Using Social Tagging

Abstract

A method and system for using social tagging to identify a search engine user's intent are described. A search engine selects a set of pages that are relevant to a query. The engine determines neighbors of these pages and groups the neighbors into topical clusters. For each cluster, the engine determines tags that a community of users has frequently associated with pages in that cluster. For each cluster, the engine matches that cluster's dominant tags with phrases in various intent lists. By matching a particular cluster's tags to various lists, an intent corresponding to that particular cluster is determined. For each cluster's intent, the search engine may present, with query results, types of content that correspond especially to that intent (e.g., a map for a location intent, possibly along with driving directions). Additionally or alternatively, for each such intent, the search engine may format the query results in a manner that suits the intent.

Dependencies are inferred from the claim text.