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.
Description
“Serving Each User”: Supporting Different Eating Goals Through a Multi-List Recommender Interface | Fifteenth ACM Conference on Recommender Systems
%0 Conference Paper
%1 Starke_2021
%A Starke, Alain
%A Asotic, Edis
%A Trattner, Christoph
%B Fifteenth ACM Conference on Recommender Systems
%D 2021
%I ACM
%K RecSys2021 carousel explanation food-recommender recommender
%P 124-132
%R 10.1145/3460231.3474232
%T Serving Each User: Supporting Different Eating Goals Through a Multi-List Recommender Interface
%U https://doi.org/10.1145%2F3460231.3474232
%X 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.
@inproceedings{Starke_2021,
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.},
added-at = {2021-09-28T15:13:15.000+0200},
author = {Starke, Alain and Asotic, Edis and Trattner, Christoph},
biburl = {https://www.bibsonomy.org/bibtex/25cce883788c83c4d2ede1222ec88df2c/brusilovsky},
booktitle = {Fifteenth {ACM} Conference on Recommender Systems},
description = {“Serving Each User”: Supporting Different Eating Goals Through a Multi-List Recommender Interface | Fifteenth ACM Conference on Recommender Systems},
doi = {10.1145/3460231.3474232},
interhash = {e578c5ef84bcc9e5cdfe94d0e9197b1d},
intrahash = {5cce883788c83c4d2ede1222ec88df2c},
keywords = {RecSys2021 carousel explanation food-recommender recommender},
month = sep,
pages = {124-132},
publisher = {{ACM}},
timestamp = {2023-06-05T01:10:21.000+0200},
title = {Serving Each User: Supporting Different Eating Goals Through a Multi-List Recommender Interface},
url = {https://doi.org/10.1145%2F3460231.3474232},
year = 2021
}