Link to the University of Pittsburgh Homepage
Link to the University Library System Homepage Link to the Contact Us Form

An interactive and interpretable interface for diversity in recommender systems

Tsai, CH (2017) An interactive and interpretable interface for diversity in recommender systems. In: UNSPECIFIED.

[img]
Preview
PDF
Available under License : See the attached license file.

Download (238kB) | Preview
[img] Plain Text (licence)
Available under License : See the attached license file.

Download (1kB)

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. Copyright held by the owner/author(s).


Share

Citation/Export:
Social Networking:
Share |

Details

Item Type: Conference or Workshop Item (UNSPECIFIED)
Status: Published
Creators/Authors:
CreatorsEmailPitt UsernameORCID
Tsai, CHcht77@pitt.eduCHT77
Date: 7 March 2017
Date Type: Publication
Journal or Publication Title: International Conference on Intelligent User Interfaces, Proceedings IUI
Page Range: 225 - 228
Event Type: Conference
DOI or Unique Handle: 10.1145/3030024.3038292
Refereed: Yes
ISBN: 9781450348935
Date Deposited: 09 Aug 2017 15:19
Last Modified: 17 Oct 2017 20:55
URI: http://d-scholarship.pitt.edu/id/eprint/32807

Metrics

Monthly Views for the past 3 years

Plum Analytics

Altmetric.com


Actions (login required)

View Item View Item