"Serving Each User": Supporting different eating goals through a multi-list recommender interface

Alain Starke; Edis Asotic; Christoph Trattner

doi:10.1145/3460231.3474232

"Serving Each User": Supporting different eating goals through a multi-list recommender interface

Alain Starke, Edis Asotic, Christoph Trattner

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

29 Citations (Scopus)

Abstract

Food recommender systems optimize towards a user's current preferences. However, appetites may vary, in the sense that users might seek healthy recipes today and look for unhealthy meals tomorrow. In this paper, we propose a novel approach in the food domain to diversify recommendations across different lists to 'serve' different users goals, compiled in a multi-list food recommender interface. We evaluated our interface in a 2 (single list vs multiple lists) x 2 (without or with explanations) between-subject user study (N = 366), linking choice behavior and evaluation aspects through the user experience framework. Our multi-list interface was evaluated more favorably than a single-list interface, in terms of diversity and choice satisfaction. Moreover, it triggered changes in food choices, even though these choices were less healthy than those made in the single-list interface.

Original language	English
Title of host publication	RecSys 2021 - 15th ACM Conference on Recommender Systems
Publisher	Association for Computing Machinery, Inc.
Pages	124-132
Number of pages	9
ISBN (Electronic)	978-1-4503-8458-2
DOIs	https://doi.org/10.1145/3460231.3474232
Publication status	Published - Sept 2021
Externally published	Yes
Event	15th ACM Conference on Recommender Systems, RecSys 2021 - Virtual, Online Beurs van Berlage, Amsterdam, Netherlands Duration: 27 Sept 2021 → 1 Oct 2021 Conference number: 15 https://recsys.acm.org/recsys21/

Conference

Conference	15th ACM Conference on Recommender Systems, RecSys 2021
Abbreviated title	RecSys 2021
Country/Territory	Netherlands
City	Amsterdam
Period	27/09/21 → 1/10/21
Internet address	https://recsys.acm.org/recsys21/

Funding

This work was supported by the Research Council of Norway with funding to MediaFutures: Research Centre for Responsible Media Technology and Innovation, through the Centre for Research-based Innovation scheme, project number 309339.

Keywords

Food
Goals
Health
Nudges
Recommender Systems
User Experience

Access to Document

10.1145/3460231.3474232

Cite this

@inproceedings{3887e0a848784e0897d271e9836939cf,

title = "{"}Serving Each User{"}: Supporting different eating goals through a multi-list recommender interface",

abstract = "Food recommender systems optimize towards a user's current preferences. However, appetites may vary, in the sense that users might seek healthy recipes today and look for unhealthy meals tomorrow. In this paper, we propose a novel approach in the food domain to diversify recommendations across different lists to 'serve' different users goals, compiled in a multi-list food recommender interface. We evaluated our interface in a 2 (single list vs multiple lists) x 2 (without or with explanations) between-subject user study (N = 366), linking choice behavior and evaluation aspects through the user experience framework. Our multi-list interface was evaluated more favorably than a single-list interface, in terms of diversity and choice satisfaction. Moreover, it triggered changes in food choices, even though these choices were less healthy than those made in the single-list interface. ",

keywords = "Food, Goals, Health, Nudges, Recommender Systems, User Experience",

author = "Alain Starke and Edis Asotic and Christoph Trattner",

note = "Funding Information: This work was supported by the Research Council of Norway with funding to MediaFutures: Research Centre for Responsible Media Technology and Innovation, through the Centre for Research-based Innovation scheme, project number 309339. Publisher Copyright: {\textcopyright} 2021 ACM.; 15th ACM Conference on Recommender Systems, RecSys 2021, RecSys 2021 ; Conference date: 27-09-2021 Through 01-10-2021",

year = "2021",

month = sep,

doi = "10.1145/3460231.3474232",

language = "English",

pages = "124--132",

booktitle = "RecSys 2021 - 15th ACM Conference on Recommender Systems",

publisher = "Association for Computing Machinery, Inc.",

address = "United States",

url = "https://recsys.acm.org/recsys21/",

}

Starke, A, Asotic, E & Trattner, C 2021, "Serving Each User": Supporting different eating goals through a multi-list recommender interface. in RecSys 2021 - 15th ACM Conference on Recommender Systems. Association for Computing Machinery, Inc., pp. 124-132, 15th ACM Conference on Recommender Systems, RecSys 2021, Amsterdam, Netherlands, 27/09/21. https://doi.org/10.1145/3460231.3474232

"Serving Each User": Supporting different eating goals through a multi-list recommender interface. / Starke, Alain; Asotic, Edis; Trattner, Christoph.
RecSys 2021 - 15th ACM Conference on Recommender Systems. Association for Computing Machinery, Inc., 2021. p. 124-132.

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

TY - GEN

T1 - "Serving Each User"

T2 - 15th ACM Conference on Recommender Systems, RecSys 2021

AU - Starke, Alain

AU - Asotic, Edis

AU - Trattner, Christoph

N1 - Conference code: 15

PY - 2021/9

Y1 - 2021/9

N2 - Food recommender systems optimize towards a user's current preferences. However, appetites may vary, in the sense that users might seek healthy recipes today and look for unhealthy meals tomorrow. In this paper, we propose a novel approach in the food domain to diversify recommendations across different lists to 'serve' different users goals, compiled in a multi-list food recommender interface. We evaluated our interface in a 2 (single list vs multiple lists) x 2 (without or with explanations) between-subject user study (N = 366), linking choice behavior and evaluation aspects through the user experience framework. Our multi-list interface was evaluated more favorably than a single-list interface, in terms of diversity and choice satisfaction. Moreover, it triggered changes in food choices, even though these choices were less healthy than those made in the single-list interface.

AB - Food recommender systems optimize towards a user's current preferences. However, appetites may vary, in the sense that users might seek healthy recipes today and look for unhealthy meals tomorrow. In this paper, we propose a novel approach in the food domain to diversify recommendations across different lists to 'serve' different users goals, compiled in a multi-list food recommender interface. We evaluated our interface in a 2 (single list vs multiple lists) x 2 (without or with explanations) between-subject user study (N = 366), linking choice behavior and evaluation aspects through the user experience framework. Our multi-list interface was evaluated more favorably than a single-list interface, in terms of diversity and choice satisfaction. Moreover, it triggered changes in food choices, even though these choices were less healthy than those made in the single-list interface.

KW - Food

KW - Goals

KW - Health

KW - Nudges

KW - Recommender Systems

KW - User Experience

UR - http://www.scopus.com/inward/record.url?scp=85115614217&partnerID=8YFLogxK

U2 - 10.1145/3460231.3474232

DO - 10.1145/3460231.3474232

M3 - Conference contribution

AN - SCOPUS:85115614217

SP - 124

EP - 132

BT - RecSys 2021 - 15th ACM Conference on Recommender Systems

PB - Association for Computing Machinery, Inc.

Y2 - 27 September 2021 through 1 October 2021

ER -

"Serving Each User": Supporting different eating goals through a multi-list recommender interface

Abstract

Conference

Funding

Keywords

Access to Document

Other files and links

Fingerprint

Cite this