Serendipity in recommender systems beyond the algorithm: A feature repository and experimental design

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

Standard

Serendipity in recommender systems beyond the algorithm: A feature repository and experimental design. / Smets, Annelien; Michiels, Lien; Bogers, Toine; Björneborn, Lennart.

Proceedings of the 9th Joint Workshop on Interfaces and Human Decision Making for Recommender Systems (IntRS’22), Seattle, US, September 22, 2022, co-located with 16th ACM Conference on Recommender Systems (RecSys 2022). ACM Press, 2022. p. 46-66.

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

Harvard

Smets, A, Michiels, L, Bogers, T & Björneborn, L 2022, Serendipity in recommender systems beyond the algorithm: A feature repository and experimental design. in Proceedings of the 9th Joint Workshop on Interfaces and Human Decision Making for Recommender Systems (IntRS’22), Seattle, US, September 22, 2022, co-located with 16th ACM Conference on Recommender Systems (RecSys 2022). ACM Press, pp. 46-66, 9th Joint Workshop on Interfaces and Human Decision Making for Recommender Systems (IntRS’22), Seattle, Washington, United States, 22/09/2022. <http://ceur-ws.org/Vol-3222/paper4.pdf >

APA

Smets, A., Michiels, L., Bogers, T., & Björneborn, L. (2022). Serendipity in recommender systems beyond the algorithm: A feature repository and experimental design. In Proceedings of the 9th Joint Workshop on Interfaces and Human Decision Making for Recommender Systems (IntRS’22), Seattle, US, September 22, 2022, co-located with 16th ACM Conference on Recommender Systems (RecSys 2022) (pp. 46-66). ACM Press. http://ceur-ws.org/Vol-3222/paper4.pdf

Vancouver

Smets A, Michiels L, Bogers T, Björneborn L. Serendipity in recommender systems beyond the algorithm: A feature repository and experimental design. In Proceedings of the 9th Joint Workshop on Interfaces and Human Decision Making for Recommender Systems (IntRS’22), Seattle, US, September 22, 2022, co-located with 16th ACM Conference on Recommender Systems (RecSys 2022). ACM Press. 2022. p. 46-66

Author

Smets, Annelien ; Michiels, Lien ; Bogers, Toine ; Björneborn, Lennart. / Serendipity in recommender systems beyond the algorithm: A feature repository and experimental design. Proceedings of the 9th Joint Workshop on Interfaces and Human Decision Making for Recommender Systems (IntRS’22), Seattle, US, September 22, 2022, co-located with 16th ACM Conference on Recommender Systems (RecSys 2022). ACM Press, 2022. pp. 46-66

Bibtex

@inproceedings{a73de69b003b47fe82f1b3ab766ff0b7,
title = "Serendipity in recommender systems beyond the algorithm: A feature repository and experimental design",
abstract = "Serendipity in recommender systems is ought to improve the quality and usefulness of recommendations. However, despite the increasing amount of attention in both research and practice, designing for serendipity in recommenders continues to be challenging. We argue that this is due to the narrow interpretation of serendipity as an evaluation metric for algorithmic performance. Instead, we venture that serendipity in recommenders should be understood as a user experience that can be influenced by a broad range of system features that go beyond mere algorithmic improvements. In this paper, we propose a first feature repository for serendipity in recommender systems that identifies which elements could theoretically contribute to serendipitous encounters. These include design aspects related to the content, user interface and information access. Furthermore, we outline an experimental design for evaluating the influence of these features on the serendipitous encounters by users. The experiment design is described in such a way that it can be easily reproduced in different recommendation scenarios to contribute empirical insights in various settings. This work aspires to represent a first step towards fostering a more integrated and user-centric view on serendipity in recommender systems and thereby improving our ability to design for it.",
keywords = "Faculty of Humanities, Serendipity, Recommender systems, Affordances, Design, Interaction, Evaluation",
author = "Annelien Smets and Lien Michiels and Toine Bogers and Lennart Bj{\"o}rneborn",
year = "2022",
month = sep,
day = "24",
language = "English",
pages = "46--66",
booktitle = "Proceedings of the 9th Joint Workshop on Interfaces and Human Decision Making for Recommender Systems (IntRS{\textquoteright}22), Seattle, US, September 22, 2022, co-located with 16th ACM Conference on Recommender Systems (RecSys 2022)",
publisher = "ACM Press",
note = "9th Joint Workshop on Interfaces and Human Decision Making for Recommender Systems (IntRS{\textquoteright}22) : co-located with 16th ACM Conference on Recommender Systems (RecSys 2022), Seattle, US, September 18-23, 2022, IntRS{\textquoteright}22 ; Conference date: 22-09-2022",
url = "http://ceur-ws.org/Vol-3222",

}

RIS

TY - GEN

T1 - Serendipity in recommender systems beyond the algorithm: A feature repository and experimental design

AU - Smets, Annelien

AU - Michiels, Lien

AU - Bogers, Toine

AU - Björneborn, Lennart

PY - 2022/9/24

Y1 - 2022/9/24

N2 - Serendipity in recommender systems is ought to improve the quality and usefulness of recommendations. However, despite the increasing amount of attention in both research and practice, designing for serendipity in recommenders continues to be challenging. We argue that this is due to the narrow interpretation of serendipity as an evaluation metric for algorithmic performance. Instead, we venture that serendipity in recommenders should be understood as a user experience that can be influenced by a broad range of system features that go beyond mere algorithmic improvements. In this paper, we propose a first feature repository for serendipity in recommender systems that identifies which elements could theoretically contribute to serendipitous encounters. These include design aspects related to the content, user interface and information access. Furthermore, we outline an experimental design for evaluating the influence of these features on the serendipitous encounters by users. The experiment design is described in such a way that it can be easily reproduced in different recommendation scenarios to contribute empirical insights in various settings. This work aspires to represent a first step towards fostering a more integrated and user-centric view on serendipity in recommender systems and thereby improving our ability to design for it.

AB - Serendipity in recommender systems is ought to improve the quality and usefulness of recommendations. However, despite the increasing amount of attention in both research and practice, designing for serendipity in recommenders continues to be challenging. We argue that this is due to the narrow interpretation of serendipity as an evaluation metric for algorithmic performance. Instead, we venture that serendipity in recommenders should be understood as a user experience that can be influenced by a broad range of system features that go beyond mere algorithmic improvements. In this paper, we propose a first feature repository for serendipity in recommender systems that identifies which elements could theoretically contribute to serendipitous encounters. These include design aspects related to the content, user interface and information access. Furthermore, we outline an experimental design for evaluating the influence of these features on the serendipitous encounters by users. The experiment design is described in such a way that it can be easily reproduced in different recommendation scenarios to contribute empirical insights in various settings. This work aspires to represent a first step towards fostering a more integrated and user-centric view on serendipity in recommender systems and thereby improving our ability to design for it.

KW - Faculty of Humanities

KW - Serendipity

KW - Recommender systems

KW - Affordances

KW - Design

KW - Interaction

KW - Evaluation

UR - http://ceur-ws.org/Vol-3222

M3 - Article in proceedings

SP - 46

EP - 66

BT - Proceedings of the 9th Joint Workshop on Interfaces and Human Decision Making for Recommender Systems (IntRS’22), Seattle, US, September 22, 2022, co-located with 16th ACM Conference on Recommender Systems (RecSys 2022)

PB - ACM Press

T2 - 9th Joint Workshop on Interfaces and Human Decision Making for Recommender Systems (IntRS’22)

Y2 - 22 September 2022

ER -

ID: 322278290