Source
Automatically imported from: http://commons.somewhere.com:80/rre/1996/InfoSpiders.Distributed..html
Content
This web service brought to you by Somewhere.Com, LLC.
InfoSpiders: Distributed Agents for Information Retrieval on the Web
``` ---
This message was forwarded through the Red Rock Eater News Service (RRE). Send any replies to the original author, listed in the From: field below. You are welcome to send the message along to others but please do not use the "redirect" command. For information on RRE, including instructions for (un)subscribing, send an empty message to rre-help@weber.ucsd.edu
---
Date: Wed, 23 Oct 1996 11:57:19 -0700
From: Lisa Bodecker
ARTIFICIAL INTELLIGENCE SEMINAR Department of Computer Science and Engineering University of California, San Diego
Title: "InfoSpiders: Distributed Agents for Information Retrieval on the Web"
Speaker: Filippo Menczer
ABSTRACT: We propose a model, inspired by recent artificial life theory, applied to the problem of retrieving information from a large, distributed collection of documents such as the World Wide Web. A population of agents is evolved under density dependent selection for the task of locating information for the user. The energy necessary for survival is obtained from both environment and user in exchange for appropriate information. By competing for relevant documents, the agents robustly adapt to their information environment and are allocated to efficiently exploit shared resources. To illustrate the roles played by document locality, adaptive search strategies, and relevance feedback in the information gathering process, we have implemented a client-based prototype of the InfoSpiders algorithm. The demo shows how the user can initialize a population of agents from any set of personal bookmarks, possibly resulting from a query previously submitted to some index-based search engine. Then the InfoSpiders browse neighborhoods of the information environments, guided by its semantic structure, looking for documents that match the user's query. During this distributed exploration phase, they discover portions of the WWW graph that seem relevant to the user's query and adapt their search strategies to the local characteristics of the graph. The user interacts asynchronously with the agents, via relevance assessments that provide feedback to the population by replenishing resources near interesting documents. Agents are not only biased by relevance feedback, but also adapt to it over time. ```
This web service brought to you by Somewhere.Com, LLC.