An Interactive and Interpretable Interface for Diversity in Recommender Systems

Authors

Chun-Hua Tsai, University of Nebraska at OmahaFollow

Author ORCID Identifier

Tsai - https://orcid.org/0000-0001-9188-0362

Document Type

Article

Publication Date

3-7-2017

Publication Title

Proceedings of the 22nd International Conference on Intelligent User Interfaces Companion

First Page

225

Last Page

228

Abstract

Offering diversity in the output of a recommender system is an active research question. Most of the current approaches focus on Top-N optimization, which results in poor user insight and accuracy trade-off. However, little is known about how an interactive interface can help with this issue. This pilot study shows that a multidimensional visualization promotes diversity among the recommended items. This finding motivated future work to provide diversity in recommender system by visualizing multivariate data through an interpretable and interactive interface.

Comments

Copyright © 2017 by Authors

Recommended Citation

Tsai, C. H. (2017). An interactive and interpretable interface for diversity in recommender systems. In Proceedings of the 22nd International Conference on Intelligent User Interfaces Companion (IUI’17) (pp. 225-228). https://doi.org/10.1145/3030024.3038292