Providing Control and Transparency in a Social Recommender System for Academic Conferences
C. Tsai, and P. Brusilovsky. Proceedings of the 25th Conference on User Modeling, Adaptation and Personalization, page 313--317. New York, NY, USA, ACM, (2017)
DOI: 10.1145/3079628.3079701
Abstract
A social recommender system aims to provide useful suggestion to the user and prevent social overload problem. Most of the research efforts are spent on push high relevant item on top of the ranked list, using a weight ensemble approach. However, we argue the ``learned'' static fusion is not enough to specific contexts. In this paper, we develop a series visual recommendation components and control panel for the user to interact with the recommendation result of an academic conference. The system offers a better recommendation transparency and user-driven fusion through recommended sources. The experiment result shows the user did fuse the different recommended sources and exploration patterns among tasks. The post-study survey is positively associated with the system and explanation function effectiveness. This finding shed light on the future research of design a recommender system with human intervention and the interface beyond the static ranked list.
%0 Conference Paper
%1 citeulike:14391745
%A Tsai, Chun H.
%A Brusilovsky, Peter
%B Proceedings of the 25th Conference on User Modeling, Adaptation and Personalization
%C New York, NY, USA
%D 2017
%I ACM
%K recommender social-network transparency umap2017 user-control
%P 313--317
%R 10.1145/3079628.3079701
%T Providing Control and Transparency in a Social Recommender System for Academic Conferences
%U http://dx.doi.org/10.1145/3079628.3079701
%X A social recommender system aims to provide useful suggestion to the user and prevent social overload problem. Most of the research efforts are spent on push high relevant item on top of the ranked list, using a weight ensemble approach. However, we argue the ``learned'' static fusion is not enough to specific contexts. In this paper, we develop a series visual recommendation components and control panel for the user to interact with the recommendation result of an academic conference. The system offers a better recommendation transparency and user-driven fusion through recommended sources. The experiment result shows the user did fuse the different recommended sources and exploration patterns among tasks. The post-study survey is positively associated with the system and explanation function effectiveness. This finding shed light on the future research of design a recommender system with human intervention and the interface beyond the static ranked list.
%@ 978-1-4503-4635-1
@inproceedings{citeulike:14391745,
abstract = {{A social recommender system aims to provide useful suggestion to the user and prevent social overload problem. Most of the research efforts are spent on push high relevant item on top of the ranked list, using a weight ensemble approach. However, we argue the ``learned'' static fusion is not enough to specific contexts. In this paper, we develop a series visual recommendation components and control panel for the user to interact with the recommendation result of an academic conference. The system offers a better recommendation transparency and user-driven fusion through recommended sources. The experiment result shows the user did fuse the different recommended sources and exploration patterns among tasks. The post-study survey is positively associated with the system and explanation function effectiveness. This finding shed light on the future research of design a recommender system with human intervention and the interface beyond the static ranked list.}},
added-at = {2018-03-19T12:24:51.000+0100},
address = {New York, NY, USA},
author = {Tsai, Chun H. and Brusilovsky, Peter},
biburl = {https://www.bibsonomy.org/bibtex/291aa82aa4fb605b6762cf8debe327e23/aho},
booktitle = {Proceedings of the 25th Conference on User Modeling, Adaptation and Personalization},
citeulike-article-id = {14391745},
citeulike-linkout-0 = {http://portal.acm.org/citation.cfm?id=3079701},
citeulike-linkout-1 = {http://dx.doi.org/10.1145/3079628.3079701},
doi = {10.1145/3079628.3079701},
interhash = {9c1bb482836e3270ff6a6d2d31486a91},
intrahash = {91aa82aa4fb605b6762cf8debe327e23},
isbn = {978-1-4503-4635-1},
keywords = {recommender social-network transparency umap2017 user-control},
location = {Bratislava, Slovakia},
pages = {313--317},
posted-at = {2017-07-12 10:24:28},
priority = {2},
publisher = {ACM},
series = {UMAP '17},
timestamp = {2018-03-19T12:24:51.000+0100},
title = {{Providing Control and Transparency in a Social Recommender System for Academic Conferences}},
url = {http://dx.doi.org/10.1145/3079628.3079701},
year = 2017
}