Virtual extension: Information seeking: Convergence of search, recommendations, and advertising

Hector Garcia-Molina, Georgia Koutrika, Aditya Parameswaran

Research output: Contribution to journalReview articlepeer-review


The methodology to use information needs amidst a preponderance of data is described. A recommendation mechanism typically does not use an explicit query but rather analyzes the user context. For example, in an electronic commerce site, when a user purchases one object, he may be shown a set of similar objects, or objects that other people have purchased together with the just purchased object. The row labeled 'Beneficiary' refers to whether the interests of the user or the information provider have priority. The input to the filtering stage is a set of objects and a filtering or Boolean sub-query, while the output is the subset of the objects that satisfy the sub-query. Another example of a collaborative approach is that of the discovery of sets of products usually purchased together by many independent buyers, which is applied to recommend to a shopper other products related to the product currently being viewed.

Original languageEnglish (US)
Pages (from-to)121-130
Number of pages10
JournalCommunications of the ACM
Issue number11
StatePublished - Nov 2011
Externally publishedYes

ASJC Scopus subject areas

  • General Computer Science


Dive into the research topics of 'Virtual extension: Information seeking: Convergence of search, recommendations, and advertising'. Together they form a unique fingerprint.

Cite this