Enhancing explainability of social recommendation using 2D graphs and word cloud visualizations

Saeed Amal; Mustafa Adam; Peter Brusilovsky; Einat Minkov; Tsvi Kuflik

doi:10.1145/3308557.3308702

Enhancing explainability of social recommendation using 2D graphs and word cloud visualizations

Saeed Amal, Mustafa Adam, Peter Brusilovsky, Einat Minkov, Tsvi Kuflik

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

1 Scopus citations

Abstract

Explainability is an important desired property of recommendation systems. We consider a graph-based recommendation approach, which generates detailed explanations to users in the form of labelled connecting relational paths and present a visualization interface intended to convey such detailed relational information in clear and intuitive manner. As initial evaluation, we performed a user study at an academic conference, recommending participants the users may be interested to meet (using <u>rsr.cloud</u>). The feedbacks were enthusiastic, indicating that the proposed visualizations of relational explanations are engaging and useful.

Original language	English
Title of host publication	Proceedings of the 24th International Conference on Intelligent User Interfaces, IUI 2019
Publisher	Association for Computing Machinery
Pages	21-22
Number of pages	2
ISBN (Electronic)	9781450366731
DOIs	https://doi.org/10.1145/3308557.3308702
State	Published - 16 Mar 2019
Externally published	Yes
Event	24th International Conference on Intelligent User Interfaces, IUI 2019 - Marina del Ray, United States Duration: 16 Mar 2019 → 20 Mar 2019

Publication series

Name	International Conference on Intelligent User Interfaces, Proceedings IUI

Conference

Conference	24th International Conference on Intelligent User Interfaces, IUI 2019
Country/Territory	United States
City	Marina del Ray
Period	16/03/19 → 20/03/19

Keywords

2D graph
Visualized social recommendation
Word cloud

ASJC Scopus subject areas

Software
Human-Computer Interaction

Access to Document

10.1145/3308557.3308702

Cite this

Amal, S., Adam, M., Brusilovsky, P., Minkov, E., & Kuflik, T. (2019). Enhancing explainability of social recommendation using 2D graphs and word cloud visualizations. In Proceedings of the 24th International Conference on Intelligent User Interfaces, IUI 2019 (pp. 21-22). (International Conference on Intelligent User Interfaces, Proceedings IUI). Association for Computing Machinery. https://doi.org/10.1145/3308557.3308702

Amal, Saeed ; Adam, Mustafa ; Brusilovsky, Peter et al. / Enhancing explainability of social recommendation using 2D graphs and word cloud visualizations. Proceedings of the 24th International Conference on Intelligent User Interfaces, IUI 2019. Association for Computing Machinery, 2019. pp. 21-22 (International Conference on Intelligent User Interfaces, Proceedings IUI).

@inproceedings{e7d6835cf8fa49a793e0a0cf39f8a01f,

title = "Enhancing explainability of social recommendation using 2D graphs and word cloud visualizations",

abstract = "Explainability is an important desired property of recommendation systems. We consider a graph-based recommendation approach, which generates detailed explanations to users in the form of labelled connecting relational paths and present a visualization interface intended to convey such detailed relational information in clear and intuitive manner. As initial evaluation, we performed a user study at an academic conference, recommending participants the users may be interested to meet (using rsr.cloud). The feedbacks were enthusiastic, indicating that the proposed visualizations of relational explanations are engaging and useful.",

keywords = "2D graph, Visualized social recommendation, Word cloud",

author = "Saeed Amal and Mustafa Adam and Peter Brusilovsky and Einat Minkov and Tsvi Kuflik",

note = "Publisher Copyright: {\textcopyright} 2019 ACM.; 24th International Conference on Intelligent User Interfaces, IUI 2019 ; Conference date: 16-03-2019 Through 20-03-2019",

year = "2019",

month = mar,

day = "16",

doi = "10.1145/3308557.3308702",

language = "English",

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

publisher = "Association for Computing Machinery",

pages = "21--22",

booktitle = "Proceedings of the 24th International Conference on Intelligent User Interfaces, IUI 2019",

}

Amal, S, Adam, M, Brusilovsky, P, Minkov, E & Kuflik, T 2019, Enhancing explainability of social recommendation using 2D graphs and word cloud visualizations. in Proceedings of the 24th International Conference on Intelligent User Interfaces, IUI 2019. International Conference on Intelligent User Interfaces, Proceedings IUI, Association for Computing Machinery, pp. 21-22, 24th International Conference on Intelligent User Interfaces, IUI 2019, Marina del Ray, United States, 16/03/19. https://doi.org/10.1145/3308557.3308702

Enhancing explainability of social recommendation using 2D graphs and word cloud visualizations. / Amal, Saeed; Adam, Mustafa; Brusilovsky, Peter et al.
Proceedings of the 24th International Conference on Intelligent User Interfaces, IUI 2019. Association for Computing Machinery, 2019. p. 21-22 (International Conference on Intelligent User Interfaces, Proceedings IUI).

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

TY - GEN

T1 - Enhancing explainability of social recommendation using 2D graphs and word cloud visualizations

AU - Amal, Saeed

AU - Adam, Mustafa

AU - Brusilovsky, Peter

AU - Minkov, Einat

AU - Kuflik, Tsvi

PY - 2019/3/16

Y1 - 2019/3/16

N2 - Explainability is an important desired property of recommendation systems. We consider a graph-based recommendation approach, which generates detailed explanations to users in the form of labelled connecting relational paths and present a visualization interface intended to convey such detailed relational information in clear and intuitive manner. As initial evaluation, we performed a user study at an academic conference, recommending participants the users may be interested to meet (using rsr.cloud). The feedbacks were enthusiastic, indicating that the proposed visualizations of relational explanations are engaging and useful.

AB - Explainability is an important desired property of recommendation systems. We consider a graph-based recommendation approach, which generates detailed explanations to users in the form of labelled connecting relational paths and present a visualization interface intended to convey such detailed relational information in clear and intuitive manner. As initial evaluation, we performed a user study at an academic conference, recommending participants the users may be interested to meet (using rsr.cloud). The feedbacks were enthusiastic, indicating that the proposed visualizations of relational explanations are engaging and useful.

KW - 2D graph

KW - Visualized social recommendation

KW - Word cloud

UR - http://www.scopus.com/inward/record.url?scp=85074451830&partnerID=8YFLogxK

U2 - 10.1145/3308557.3308702

DO - 10.1145/3308557.3308702

M3 - Conference contribution

AN - SCOPUS:85074451830

T3 - International Conference on Intelligent User Interfaces, Proceedings IUI

SP - 21

EP - 22

BT - Proceedings of the 24th International Conference on Intelligent User Interfaces, IUI 2019

PB - Association for Computing Machinery

T2 - 24th International Conference on Intelligent User Interfaces, IUI 2019

Y2 - 16 March 2019 through 20 March 2019

ER -

Amal S, Adam M, Brusilovsky P, Minkov E, Kuflik T. Enhancing explainability of social recommendation using 2D graphs and word cloud visualizations. In Proceedings of the 24th International Conference on Intelligent User Interfaces, IUI 2019. Association for Computing Machinery. 2019. p. 21-22. (International Conference on Intelligent User Interfaces, Proceedings IUI). doi: 10.1145/3308557.3308702

Enhancing explainability of social recommendation using 2D graphs and word cloud visualizations

Abstract

Publication series

Conference

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this