An interactive and interpretable interface for diversity in recommender systems

Chun Hua Tsai

doi:10.1145/3030024.3038292

An interactive and interpretable interface for diversity in recommender systems

Chun Hua Tsai

College of Information Sciences and Technology

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

8 Scopus citations

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).

Original language	English (US)
Title of host publication	IUI 2017 - Companion of the 22nd International Conference on Intelligent User Interfaces
Publisher	Association for Computing Machinery
Pages	225-228
Number of pages	4
ISBN (Electronic)	9781450348935
DOIs	https://doi.org/10.1145/3030024.3038292
State	Published - Mar 7 2017
Event	22nd International Conference on Intelligent User Interfaces, IUI 2017 - Limassol, Cyprus Duration: Mar 13 2017 → Mar 16 2017

Publication series

Name	International Conference on Intelligent User Interfaces, Proceedings IUI

Conference

Conference	22nd International Conference on Intelligent User Interfaces, IUI 2017
Country/Territory	Cyprus
City	Limassol
Period	3/13/17 → 3/16/17

All Science Journal Classification (ASJC) codes

Software
Human-Computer Interaction

Access to Document

10.1145/3030024.3038292

Cite this

@inproceedings{8fab4d3b83ea4d1c8305730e042c9f73,

title = "An interactive and interpretable interface for diversity in recommender systems",

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).",

author = "Tsai, {Chun Hua}",

year = "2017",

month = mar,

day = "7",

doi = "10.1145/3030024.3038292",

language = "English (US)",

series = "International Conference on Intelligent User Interfaces, Proceedings IUI",

publisher = "Association for Computing Machinery",

pages = "225--228",

booktitle = "IUI 2017 - Companion of the 22nd International Conference on Intelligent User Interfaces",

}

Tsai, CH 2017, An interactive and interpretable interface for diversity in recommender systems. in IUI 2017 - Companion of the 22nd International Conference on Intelligent User Interfaces. International Conference on Intelligent User Interfaces, Proceedings IUI, Association for Computing Machinery, pp. 225-228, 22nd International Conference on Intelligent User Interfaces, IUI 2017, Limassol, Cyprus, 3/13/17. https://doi.org/10.1145/3030024.3038292

An interactive and interpretable interface for diversity in recommender systems. / Tsai, Chun Hua.
IUI 2017 - Companion of the 22nd International Conference on Intelligent User Interfaces. Association for Computing Machinery, 2017. p. 225-228 (International Conference on Intelligent User Interfaces, Proceedings IUI).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - An interactive and interpretable interface for diversity in recommender systems

AU - Tsai, Chun Hua

PY - 2017/3/7

Y1 - 2017/3/7

N2 - 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).

AB - 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).

UR - http://www.scopus.com/inward/record.url?scp=85016612772&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85016612772&partnerID=8YFLogxK

U2 - 10.1145/3030024.3038292

DO - 10.1145/3030024.3038292

M3 - Conference contribution

AN - SCOPUS:85016612772

T3 - International Conference on Intelligent User Interfaces, Proceedings IUI

SP - 225

EP - 228

BT - IUI 2017 - Companion of the 22nd International Conference on Intelligent User Interfaces

PB - Association for Computing Machinery

T2 - 22nd International Conference on Intelligent User Interfaces, IUI 2017

Y2 - 13 March 2017 through 16 March 2017

ER -

An interactive and interpretable interface for diversity in recommender systems

Abstract

Publication series

Conference

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this