DMCA
Learning Information Retrieval Agents: Experiments with Automated Web Browsing (1995)
| Citations: | 139 - 3 self |
BibTeX
@INPROCEEDINGS{Balabanovic95learninginformation,
author = {Marko Balabanovic and Yoav Shoham},
title = {Learning Information Retrieval Agents: Experiments with Automated Web Browsing},
booktitle = {},
year = {1995},
pages = {13--18}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
The current exponential growth of the Internet precipitates a need for new tools to help people cope with the volume of information. To complement recent work on creating searchable indexes of the World-Wide Web and systems for filtering incoming e-mail and Usenet news articles, we describe a system which helps users keep abreast of new and interesting information. Every day it presents a selection of interesting web pages. The user evaluates each page, and given this feedback the system adapts and attempts to produce better pages the following day. We present some early results from an AI programming class to whom this was set as a project, and then describe our current implementation. Over the course of 24 days the output of our system was compared to both randomly-selected and human-selected pages. It consistently performed better than the random pages, and was better than the human-selected pages half of the time. Introduction In recent years there has been a well-publicized expl...
Keyphrases
information retrieval agent automated web browsing world-wide web interesting information current exponential growth well-publicized expl early result random page recent year system adapts new tool following day web page searchable index current implementation human-selected page recent work usenet news article human-selected page half
