Automated recommender systems predict user preferences by applying machine learning techniques to data on products, users, and past user preferences for products. Such systems have become increasingly popular in entertainment and e-commerce domains, but have thus far had little success in information-seeking domains such as identifying published research of interest. We report on several recent publications that show how recommenders can be extended to more effectively address information-seeking tasks by expanding the focus from accurate prediction of user preferences to identifying a useful set of items to recommend in response to the user's specific information need. Specific research demonstrates the value of diversity in recommendation lists, shows how users value lists of recommendations as something different from the sum of the individual recommendations within, and presents an analytic model for customizing a recommender to match user information-seeking needs.
%0 Conference Paper
%1 konstan2006lessons
%A Konstan, Joseph A.
%A McNee, Sean M.
%A Ziegler, Cai-Nicolas
%A Torres, Roberto
%A Kapoor, Nishikant
%A Riedl, John T.
%B Proceedings of the 21st National Conference on Artificial Intelligence - Volume 2
%D 2006
%I AAAI Press
%K hri human interaction paper publication recommender research
%P 1630--1633
%T Lessons on Applying Automated Recommender Systems to Information-seeking Tasks
%U http://dl.acm.org/citation.cfm?id=1597348.1597458
%X Automated recommender systems predict user preferences by applying machine learning techniques to data on products, users, and past user preferences for products. Such systems have become increasingly popular in entertainment and e-commerce domains, but have thus far had little success in information-seeking domains such as identifying published research of interest. We report on several recent publications that show how recommenders can be extended to more effectively address information-seeking tasks by expanding the focus from accurate prediction of user preferences to identifying a useful set of items to recommend in response to the user's specific information need. Specific research demonstrates the value of diversity in recommendation lists, shows how users value lists of recommendations as something different from the sum of the individual recommendations within, and presents an analytic model for customizing a recommender to match user information-seeking needs.
%@ 978-1-57735-281-5
@inproceedings{konstan2006lessons,
abstract = {Automated recommender systems predict user preferences by applying machine learning techniques to data on products, users, and past user preferences for products. Such systems have become increasingly popular in entertainment and e-commerce domains, but have thus far had little success in information-seeking domains such as identifying published research of interest. We report on several recent publications that show how recommenders can be extended to more effectively address information-seeking tasks by expanding the focus from accurate prediction of user preferences to identifying a useful set of items to recommend in response to the user's specific information need. Specific research demonstrates the value of diversity in recommendation lists, shows how users value lists of recommendations as something different from the sum of the individual recommendations within, and presents an analytic model for customizing a recommender to match user information-seeking needs.},
acmid = {1597458},
added-at = {2015-11-20T11:48:15.000+0100},
author = {Konstan, Joseph A. and McNee, Sean M. and Ziegler, Cai-Nicolas and Torres, Roberto and Kapoor, Nishikant and Riedl, John T.},
biburl = {https://www.bibsonomy.org/bibtex/2b3c520bea4573c7ce3d6a1dabbb78614/jaeschke},
booktitle = {Proceedings of the 21st National Conference on Artificial Intelligence - Volume 2},
interhash = {fe7af07b4d23c4dd86977c22ef2e026f},
intrahash = {b3c520bea4573c7ce3d6a1dabbb78614},
isbn = {978-1-57735-281-5},
keywords = {hri human interaction paper publication recommender research},
location = {Boston, Massachusetts},
numpages = {4},
pages = {1630--1633},
publisher = {AAAI Press},
series = {AAAI'06},
timestamp = {2021-06-18T10:32:57.000+0200},
title = {Lessons on Applying Automated Recommender Systems to Information-seeking Tasks},
url = {http://dl.acm.org/citation.cfm?id=1597348.1597458},
year = 2006
}