Traditional ranking models used in Web search engines rely on a static snapshot of the Web graph, basically the link structure of the Web documents. However, visitors' browsing activities indicate the importance of a document. In the traditional static models, the information on document importance conveyed by interactive browsing is neglected. The nowadays Web server/surfer model lacks the ability to take advantage of user interaction for document ranking. We enhance the ordinary Web server/surfer model with a mechanism inspired by swarm intelligence to make it possible for the Web servers to interact with Web surfers and thus obtain a proper local ranking of Web documents. The proof-of-concept implementation of our idea demonstrates the potential of our model. The mechanism can be used directly in deployed Web servers which enable on-the-fly creation of rankings for Web documents local to a Web site. The local rankings can also be used as input for the generation of global Web rankings in a decentralized way.
[1]
Brian Detlor,et al.
Web Work: Information Seeking and Knowledge Work on the World Wide Web
,
2000
.
[2]
Rajeev Motwani,et al.
The PageRank Citation Ranking : Bringing Order to the Web
,
1999,
WWW 1999.
[3]
Barbara Webb,et al.
Swarm Intelligence: From Natural to Artificial Systems
,
2002,
Connect. Sci..
[4]
Derek Wragge Morley.
The ant world
,
1953
.
[5]
Ramana Rao,et al.
Silk from a sow's ear: extracting usable structures from the Web
,
1996,
CHI.
[6]
Karl Aberer,et al.
A Framework for Decentralized Ranking in Web Information Retrieval
,
2003,
APWeb.
[7]
Paul B. Kantor,et al.
Ant World (demonstration abstract)
,
1999,
SIGIR '99.