Facetedpedia is a faceted retrieval system for information discovery and exploration in Wikipedia. Given the set of Wikipedia articles resulting from a keyword search query, Facetedpedia discovers a faceted interface for navigating the articles. The essence of our approach is to build upon the collaborative vocabulary in Wikipedia, more specifically the intensive internal hyperlinks and folksonomy (category system). Given the sheer size and complexity of Wikipedia, the space of possible choices of faceted interfaces is prohibitively large. We thus develop faceted interface discovery algorithms that optimize the ranking metrics. The details are in the references at the bottom of this page.

As a Use Case, a soccer fan, can explore articles on renowned soccer players through Nationality, clubs, games, received rewards, etc. In a Faceted Search Interface, the user progressively selects several facets and values under them, but not necessarily on all the provided facets. For instance, the user can select "Brazil" under Facet "Country", followed by “Manchester United" under "Soccer Clubs". The system will try its best to display Brazilian players who have played for "Manchester United".

Some sample query results generated in 2010: (The system performs best with keywords aiming at a set of entities.)

us action film , us country singer , us national park , album , us film star , pc game ,

computer scientist , football player , software , best seller book , american writer , interstatehighway .


[1] Facetedpedia: dynamic generation of query-dependent faceted interfaces for Wikipedia. (WWW10) [PDF] [ACM DL]
[2] Facetedpedia: enabling query-dependent faceted search for Wikipedia. (CIKM10 Demo) [PDF] [ACM DL]