PSR: Probabilistic Serendipitous Recommendations

Hyeseong Park; Kyung Whan Oh; Uran Oh

doi:10.1109/CSCI58124.2022.00144

PSR: Probabilistic Serendipitous Recommendations

Hyeseong Park, Kyung Whan Oh, Uran Oh

Department of Computer Science & Engineering

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

Abstract

Recent recommender systems studies have started focusing on accelerating serendipity to offer users diverse perspectives. However, recommending serendipitous items is known to decrease users' satisfaction due to low recommendation accuracy. In this paper, we propose a probabilistic serendipitous recommendations (PSR) model that aims to discover serendipitous items through the fully-connected combinations of unrelated user-provided information. The proposed model provides an unexpected result, while user's answers are maintained not to decrease recommendation accuracy. An online user study with 40 participants revealed that the proposed PSR model provides serendipitous items by using the intersection of usefulness and unexpectedness from the recommended results.

Original language	English
Title of host publication	Proceedings - 2022 International Conference on Computational Science and Computational Intelligence, CSCI 2022
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	790-795
Number of pages	6
ISBN (Electronic)	9798350320282
DOIs	https://doi.org/10.1109/CSCI58124.2022.00144
State	Published - 2022
Event	2022 International Conference on Computational Science and Computational Intelligence, CSCI 2022 - Las Vegas, United States Duration: 14 Dec 2022 → 16 Dec 2022

Publication series

Name	Proceedings - 2022 International Conference on Computational Science and Computational Intelligence, CSCI 2022

Conference

Conference	2022 International Conference on Computational Science and Computational Intelligence, CSCI 2022
Country/Territory	United States
City	Las Vegas
Period	14/12/22 → 16/12/22

Bibliographical note

Publisher Copyright:
© 2022 IEEE.

Keywords

bayesian inference
combinational creativity
probability
recommendation
serendipity

Access to Document

10.1109/CSCI58124.2022.00144

Cite this

Park, H., Oh, K. W., & Oh, U. (2022). PSR: Probabilistic Serendipitous Recommendations. In Proceedings - 2022 International Conference on Computational Science and Computational Intelligence, CSCI 2022 (pp. 790-795). (Proceedings - 2022 International Conference on Computational Science and Computational Intelligence, CSCI 2022). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/CSCI58124.2022.00144

Park, Hyeseong ; Oh, Kyung Whan ; Oh, Uran. / PSR : Probabilistic Serendipitous Recommendations. Proceedings - 2022 International Conference on Computational Science and Computational Intelligence, CSCI 2022. Institute of Electrical and Electronics Engineers Inc., 2022. pp. 790-795 (Proceedings - 2022 International Conference on Computational Science and Computational Intelligence, CSCI 2022).

@inproceedings{2aec3512bb4247e5b922ee41cfb0a284,

title = "PSR: Probabilistic Serendipitous Recommendations",

abstract = "Recent recommender systems studies have started focusing on accelerating serendipity to offer users diverse perspectives. However, recommending serendipitous items is known to decrease users' satisfaction due to low recommendation accuracy. In this paper, we propose a probabilistic serendipitous recommendations (PSR) model that aims to discover serendipitous items through the fully-connected combinations of unrelated user-provided information. The proposed model provides an unexpected result, while user's answers are maintained not to decrease recommendation accuracy. An online user study with 40 participants revealed that the proposed PSR model provides serendipitous items by using the intersection of usefulness and unexpectedness from the recommended results.",

keywords = "bayesian inference, combinational creativity, probability, recommendation, serendipity",

author = "Hyeseong Park and Oh, {Kyung Whan} and Uran Oh",

note = "Publisher Copyright: {\textcopyright} 2022 IEEE.; 2022 International Conference on Computational Science and Computational Intelligence, CSCI 2022 ; Conference date: 14-12-2022 Through 16-12-2022",

year = "2022",

doi = "10.1109/CSCI58124.2022.00144",

language = "English",

series = "Proceedings - 2022 International Conference on Computational Science and Computational Intelligence, CSCI 2022",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "790--795",

booktitle = "Proceedings - 2022 International Conference on Computational Science and Computational Intelligence, CSCI 2022",

}

Park, H, Oh, KW & Oh, U 2022, PSR: Probabilistic Serendipitous Recommendations. in Proceedings - 2022 International Conference on Computational Science and Computational Intelligence, CSCI 2022. Proceedings - 2022 International Conference on Computational Science and Computational Intelligence, CSCI 2022, Institute of Electrical and Electronics Engineers Inc., pp. 790-795, 2022 International Conference on Computational Science and Computational Intelligence, CSCI 2022, Las Vegas, United States, 14/12/22. https://doi.org/10.1109/CSCI58124.2022.00144

PSR: Probabilistic Serendipitous Recommendations. / Park, Hyeseong; Oh, Kyung Whan; Oh, Uran.
Proceedings - 2022 International Conference on Computational Science and Computational Intelligence, CSCI 2022. Institute of Electrical and Electronics Engineers Inc., 2022. p. 790-795 (Proceedings - 2022 International Conference on Computational Science and Computational Intelligence, CSCI 2022).

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

TY - GEN

T1 - PSR

T2 - 2022 International Conference on Computational Science and Computational Intelligence, CSCI 2022

AU - Park, Hyeseong

AU - Oh, Kyung Whan

AU - Oh, Uran

PY - 2022

Y1 - 2022

N2 - Recent recommender systems studies have started focusing on accelerating serendipity to offer users diverse perspectives. However, recommending serendipitous items is known to decrease users' satisfaction due to low recommendation accuracy. In this paper, we propose a probabilistic serendipitous recommendations (PSR) model that aims to discover serendipitous items through the fully-connected combinations of unrelated user-provided information. The proposed model provides an unexpected result, while user's answers are maintained not to decrease recommendation accuracy. An online user study with 40 participants revealed that the proposed PSR model provides serendipitous items by using the intersection of usefulness and unexpectedness from the recommended results.

AB - Recent recommender systems studies have started focusing on accelerating serendipity to offer users diverse perspectives. However, recommending serendipitous items is known to decrease users' satisfaction due to low recommendation accuracy. In this paper, we propose a probabilistic serendipitous recommendations (PSR) model that aims to discover serendipitous items through the fully-connected combinations of unrelated user-provided information. The proposed model provides an unexpected result, while user's answers are maintained not to decrease recommendation accuracy. An online user study with 40 participants revealed that the proposed PSR model provides serendipitous items by using the intersection of usefulness and unexpectedness from the recommended results.

KW - bayesian inference

KW - combinational creativity

KW - probability

KW - recommendation

KW - serendipity

UR - http://www.scopus.com/inward/record.url?scp=85172000283&partnerID=8YFLogxK

U2 - 10.1109/CSCI58124.2022.00144

DO - 10.1109/CSCI58124.2022.00144

M3 - Conference contribution

AN - SCOPUS:85172000283

T3 - Proceedings - 2022 International Conference on Computational Science and Computational Intelligence, CSCI 2022

SP - 790

EP - 795

BT - Proceedings - 2022 International Conference on Computational Science and Computational Intelligence, CSCI 2022

PB - Institute of Electrical and Electronics Engineers Inc.

Y2 - 14 December 2022 through 16 December 2022

ER -

Park H, Oh KW, Oh U. PSR: Probabilistic Serendipitous Recommendations. In Proceedings - 2022 International Conference on Computational Science and Computational Intelligence, CSCI 2022. Institute of Electrical and Electronics Engineers Inc. 2022. p. 790-795. (Proceedings - 2022 International Conference on Computational Science and Computational Intelligence, CSCI 2022). doi: 10.1109/CSCI58124.2022.00144

PSR: Probabilistic Serendipitous Recommendations

Abstract

Publication series

Conference

Bibliographical note

Keywords

Access to Document

Fingerprint

Cite this