User-controlled Hybrid Recommendation for Academic Papers
B. Rahdari, and P. Brusilovsky. Proceedings of the 24th International Conference on Intelligent User Interfaces: Companion, page 99--100. New York, NY, USA, ACM, (2019)
DOI: 10.1145/3308557.3308717
Abstract
We present Paper Tuner, a user-controlled interface for recommending papers and presentations at a research conference. The availability of multiple sources of information about user interests makes hybrid recommendation approach attractive in a conference context, but traditional static parallel hybridization makes is hard to generate a single ranking that can address different needs. We introduce a novel slider-based user interface that allows users to control the importance of different relevance source and even reverse the impact of specific sources. The log analysis of system usage during in a real conference context revealed an extensive use of sliders. Moreover, nearly half of the users applied the reverse functionality while using the sliders.
Description
User-controlled hybrid recommendation for academic papers
%0 Conference Paper
%1 Rahdari:2019:UHR:3308557.3308717
%A Rahdari, Behnam
%A Brusilovsky, Peter
%B Proceedings of the 24th International Conference on Intelligent User Interfaces: Companion
%C New York, NY, USA
%D 2019
%I ACM
%K interactive-recommender recommender transparency user-control
%P 99--100
%R 10.1145/3308557.3308717
%T User-controlled Hybrid Recommendation for Academic Papers
%U http://doi.acm.org/10.1145/3308557.3308717
%X We present Paper Tuner, a user-controlled interface for recommending papers and presentations at a research conference. The availability of multiple sources of information about user interests makes hybrid recommendation approach attractive in a conference context, but traditional static parallel hybridization makes is hard to generate a single ranking that can address different needs. We introduce a novel slider-based user interface that allows users to control the importance of different relevance source and even reverse the impact of specific sources. The log analysis of system usage during in a real conference context revealed an extensive use of sliders. Moreover, nearly half of the users applied the reverse functionality while using the sliders.
%@ 978-1-4503-6673-1
@inproceedings{Rahdari:2019:UHR:3308557.3308717,
abstract = {We present Paper Tuner, a user-controlled interface for recommending papers and presentations at a research conference. The availability of multiple sources of information about user interests makes hybrid recommendation approach attractive in a conference context, but traditional static parallel hybridization makes is hard to generate a single ranking that can address different needs. We introduce a novel slider-based user interface that allows users to control the importance of different relevance source and even reverse the impact of specific sources. The log analysis of system usage during in a real conference context revealed an extensive use of sliders. Moreover, nearly half of the users applied the reverse functionality while using the sliders.},
acmid = {3308717},
added-at = {2019-06-06T16:56:22.000+0200},
address = {New York, NY, USA},
author = {Rahdari, Behnam and Brusilovsky, Peter},
biburl = {https://www.bibsonomy.org/bibtex/2b2c21943915fe834d8c35d5778dfdaa1/brusilovsky},
booktitle = {Proceedings of the 24th International Conference on Intelligent User Interfaces: Companion},
description = {User-controlled hybrid recommendation for academic papers},
doi = {10.1145/3308557.3308717},
interhash = {f2e9ead3f16a5b513408535dda5555f8},
intrahash = {b2c21943915fe834d8c35d5778dfdaa1},
isbn = {978-1-4503-6673-1},
keywords = {interactive-recommender recommender transparency user-control},
location = {Marina del Ray, California},
numpages = {2},
pages = {99--100},
publisher = {ACM},
series = {IUI '19},
timestamp = {2019-06-06T16:56:22.000+0200},
title = {User-controlled Hybrid Recommendation for Academic Papers},
url = {http://doi.acm.org/10.1145/3308557.3308717},
year = 2019
}