Sciweavers

SIGIR
2004
ACM

Bookmark-driven Query Routing in Peer-to-Peer Web Search

14 years 5 months ago
Bookmark-driven Query Routing in Peer-to-Peer Web Search
: We consider the problem of collaborative Web search and query routing strategies in a peer-to-peer (P2P) environment. In our architecture every peer has a full-fledged search engine with a (thematically focused) crawler and a local index whose contents may be tailored to the user’s specific interest profile. Peers are autonomous and post meta-information about their bookmarks and index lists to a global directory, which is efficiently implemented in a decentralized manner using Chordstyle distributed hash tables. A query posed by one peer is first evaluated locally; if the result is unsatisfactory the query is forwarded to selected peers. These peers are chosen based on a benefit/cost measure where benefit reflects the thematic similarity of peers’ interest profiles, derived from bookmarks, and cost captures estimated peer load and response time. The meta-information that is needed for making these query routing decisions is efficiently looked up in the global directory...
Matthias Bender, Sebastian Michel, Gerhard Weikum,
Added 30 Jun 2010
Updated 30 Jun 2010
Type Conference
Year 2004
Where SIGIR
Authors Matthias Bender, Sebastian Michel, Gerhard Weikum, Christian Zimmer
Comments (0)