Recommender systems do not always generate good recommendations for users. In order to improve recommender quality, we argue that recommenders need a deeper understanding of users and their information seeking tasks. Human-Recommender Interaction (HRI) provides a framework and a methodology for understanding users, their tasks, and recommender algorithms using a common language. Further, by using an analytic process model, HRI becomes not only descriptive, but also constructive. It can help with the design and structure of a recommender system, and it can act as a bridge between user information seeking tasks and recommender algorithms.
%0 Conference Paper
%1 McNee:2006:MRB:1125451.1125660
%A McNee, Sean M.
%A Riedl, John
%A Konstan, Joseph A.
%B CHI '06 Extended Abstracts on Human Factors in Computing Systems
%C New York, NY, USA
%D 2006
%I ACM
%K recommender user-control
%P 1103--1108
%R 10.1145/1125451.1125660
%T Making Recommendations Better: An Analytic Model for Human-recommender Interaction
%U http://doi.acm.org/10.1145/1125451.1125660
%X Recommender systems do not always generate good recommendations for users. In order to improve recommender quality, we argue that recommenders need a deeper understanding of users and their information seeking tasks. Human-Recommender Interaction (HRI) provides a framework and a methodology for understanding users, their tasks, and recommender algorithms using a common language. Further, by using an analytic process model, HRI becomes not only descriptive, but also constructive. It can help with the design and structure of a recommender system, and it can act as a bridge between user information seeking tasks and recommender algorithms.
%@ 1-59593-298-4
@inproceedings{McNee:2006:MRB:1125451.1125660,
abstract = {Recommender systems do not always generate good recommendations for users. In order to improve recommender quality, we argue that recommenders need a deeper understanding of users and their information seeking tasks. Human-Recommender Interaction (HRI) provides a framework and a methodology for understanding users, their tasks, and recommender algorithms using a common language. Further, by using an analytic process model, HRI becomes not only descriptive, but also constructive. It can help with the design and structure of a recommender system, and it can act as a bridge between user information seeking tasks and recommender algorithms.},
acmid = {1125660},
added-at = {2019-06-20T22:39:08.000+0200},
address = {New York, NY, USA},
author = {McNee, Sean M. and Riedl, John and Konstan, Joseph A.},
biburl = {https://www.bibsonomy.org/bibtex/200ec3d680e2624731a64faeb2abfd063/brusilovsky},
booktitle = {CHI '06 Extended Abstracts on Human Factors in Computing Systems},
description = {Making recommendations better},
doi = {10.1145/1125451.1125660},
interhash = {54327ca905ef60d2d1817e0de1fb9d40},
intrahash = {00ec3d680e2624731a64faeb2abfd063},
isbn = {1-59593-298-4},
keywords = {recommender user-control},
location = {Montr\&\#233;al, Qu\&\#233;bec, Canada},
numpages = {6},
pages = {1103--1108},
publisher = {ACM},
series = {CHI EA '06},
timestamp = {2019-06-20T22:39:08.000+0200},
title = {Making Recommendations Better: An Analytic Model for Human-recommender Interaction},
url = {http://doi.acm.org/10.1145/1125451.1125660},
year = 2006
}