Inferring user intent in web search by exploiting social annotations
José M. Conde, David Vallet, Pablo Castells · 2010
In this paper, we present a folksonomy-based approach for implicit user intent extraction during a Web search process. We present a number of result re-ranking techniques based on this representation that can be applied to any Web search engine. We perform a user experiment the results of which indicate that this type of representation is better at context extraction than using the actual textual content of the document.