Leveraging Interfaces to Improve Recommendation Diversity
C. Tsai, and P. Brusilovsky. Adjunct Publication of the 25th Conference on User Modeling, Adaptation and Personalization, page 65--70. New York, NY, USA, ACM, (2017)
DOI: 10.1145/3099023.3099073
Abstract
Increasing diversity in the output of a recommender system is an active research question for solving a long-tail issue. Most of the current approaches have focused on ranked list optimization to improve recommendation diversity. However, little is known about the effect that a visual interface can have on this issue. This paper shows that a multidimensional visualization promotes diversity of social exploration in the context of an academic conference. Our study shows a significant difference in the exploration pattern between ranked list and visual interfaces. The results show that a visual interface can help the user explore a a more diverse set of recommended items.
Description
Leveraging Interfaces to Improve Recommendation Diversity
%0 Conference Paper
%1 Tsai:2017:LII:3099023.3099073
%A Tsai, Chun-Hua
%A Brusilovsky, Peter
%B Adjunct Publication of the 25th Conference on User Modeling, Adaptation and Personalization
%C New York, NY, USA
%D 2017
%I ACM
%K adaptive-visualization diversity information-visualization myown recommender umap2017 user-control
%P 65--70
%R 10.1145/3099023.3099073
%T Leveraging Interfaces to Improve Recommendation Diversity
%U http://doi.acm.org/10.1145/3099023.3099073
%X Increasing diversity in the output of a recommender system is an active research question for solving a long-tail issue. Most of the current approaches have focused on ranked list optimization to improve recommendation diversity. However, little is known about the effect that a visual interface can have on this issue. This paper shows that a multidimensional visualization promotes diversity of social exploration in the context of an academic conference. Our study shows a significant difference in the exploration pattern between ranked list and visual interfaces. The results show that a visual interface can help the user explore a a more diverse set of recommended items.
%@ 978-1-4503-5067-9
@inproceedings{Tsai:2017:LII:3099023.3099073,
abstract = {Increasing diversity in the output of a recommender system is an active research question for solving a long-tail issue. Most of the current approaches have focused on ranked list optimization to improve recommendation diversity. However, little is known about the effect that a visual interface can have on this issue. This paper shows that a multidimensional visualization promotes diversity of social exploration in the context of an academic conference. Our study shows a significant difference in the exploration pattern between ranked list and visual interfaces. The results show that a visual interface can help the user explore a a more diverse set of recommended items.},
acmid = {3099073},
added-at = {2017-07-18T16:47:38.000+0200},
address = {New York, NY, USA},
author = {Tsai, Chun-Hua and Brusilovsky, Peter},
biburl = {https://www.bibsonomy.org/bibtex/2bd589f19c4ba4e2ccf20dd1af69b937b/brusilovsky},
booktitle = {Adjunct Publication of the 25th Conference on User Modeling, Adaptation and Personalization},
description = {Leveraging Interfaces to Improve Recommendation Diversity},
doi = {10.1145/3099023.3099073},
interhash = {f5ff11cdb6eb4a52fe0425ab48d9e95a},
intrahash = {bd589f19c4ba4e2ccf20dd1af69b937b},
isbn = {978-1-4503-5067-9},
keywords = {adaptive-visualization diversity information-visualization myown recommender umap2017 user-control},
location = {Bratislava, Slovakia},
numpages = {6},
pages = {65--70},
publisher = {ACM},
series = {UMAP '17},
timestamp = {2017-07-18T16:47:38.000+0200},
title = {Leveraging Interfaces to Improve Recommendation Diversity},
url = {http://doi.acm.org/10.1145/3099023.3099073},
year = 2017
}