SmartEats: Investigating the Effects of Customizable Conversational Agent in Dietary Recommendations

Minhui Liang; Jinping Wang; Yuhan Luo

doi:10.1145/3719160.3736635

SmartEats: Investigating the Effects of Customizable Conversational Agent in Dietary Recommendations

Minhui Liang
, Jinping Wang
, Yuhan Luo^*

^*Corresponding author for this work

Department of Computer Science

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

6 Citations (Scopus)

Abstract

In conversational recommender systems (CRS), the communication characteristics exhibited by the conversational agent (CA) can greatly shape user experience and their perceptions of the recommendation quality. Yet, prior work often adopts a one-size-fits-all approach, leaving the potential benefits of CA customizability—allowing users to tailor agent traits to their preferences—largely unexplored. We examine this gap in the context of dietary recommendations by introducing SmartEats, a CRS featuring a CA that can be customized by users. Through a between-subjects experiment (N = 214), we compared SmartEats to a non-customizable baseline, and followed up with participants after one week to understand whether and how the recommendations affect their food choices. We found that CA customizability directly improved participants’ immediate experience and indirectly enhanced their ability to later recall the recommendations. Reflecting on the findings, we discuss opportunities for CRS to enhance health and well-being by leveraging the customizability of emerging AI technologies. © 2025 Copyright held by the owner/author(s).

Original language	English
Title of host publication	CUI '25
Subtitle of host publication	Proceedings of the 7th ACM Conference on Conversational User Interfaces
Editors	Jaisie Sin, Edith Law, Jim Wallace, Cosmin Munteanu, Danai Korre
Publisher	Association for Computing Machinery
Pages	1-16
ISBN (Print)	9798400715273
DOIs	https://doi.org/10.1145/3719160.3736635
Publication status	Published - Jul 2025
Event	7th ACM Conference on Conversational User Interfaces (CUI 2025) - Waterloo, Canada Duration: 8 Jul 2025 → 10 Jul 2025 https://cui.acm.org/2025/

Conference

Conference	7th ACM Conference on Conversational User Interfaces (CUI 2025)
Place	Canada
City	Waterloo
Period	8/07/25 → 10/07/25
Internet address	https://cui.acm.org/2025/

Funding

This project was supported by City University of Hong Kong (#9610597 and #9229183).

Research Keywords

conversational recommender system
large language model
dietary recommendation
health behavior

Access Output

10.1145/3719160.3736635

Other Access Options

Check CityUHK Library

Permanent Link

Right click to copy link

Cite this

Liang, M., Wang, J., & Luo, Y. (2025). SmartEats: Investigating the Effects of Customizable Conversational Agent in Dietary Recommendations. In J. Sin, E. Law, J. Wallace, C. Munteanu, & D. Korre (Eds.), CUI '25: Proceedings of the 7th ACM Conference on Conversational User Interfaces (pp. 1-16). Article 63 Association for Computing Machinery. https://doi.org/10.1145/3719160.3736635

@inproceedings{1427d837ac86422b91d8992f9b590dbe,

title = "SmartEats: Investigating the Effects of Customizable Conversational Agent in Dietary Recommendations",

abstract = "In conversational recommender systems (CRS), the communication characteristics exhibited by the conversational agent (CA) can greatly shape user experience and their perceptions of the recommendation quality. Yet, prior work often adopts a one-size-fits-all approach, leaving the potential benefits of CA customizability—allowing users to tailor agent traits to their preferences—largely unexplored. We examine this gap in the context of dietary recommendations by introducing SmartEats, a CRS featuring a CA that can be customized by users. Through a between-subjects experiment (N = 214), we compared SmartEats to a non-customizable baseline, and followed up with participants after one week to understand whether and how the recommendations affect their food choices. We found that CA customizability directly improved participants{\textquoteright} immediate experience and indirectly enhanced their ability to later recall the recommendations. Reflecting on the findings, we discuss opportunities for CRS to enhance health and well-being by leveraging the customizability of emerging AI technologies. {\textcopyright} 2025 Copyright held by the owner/author(s).",

keywords = "conversational recommender system, large language model, dietary recommendation, health behavior",

author = "Minhui Liang and Jinping Wang and Yuhan Luo",

year = "2025",

month = jul,

doi = "10.1145/3719160.3736635",

language = "English",

isbn = "9798400715273",

pages = "1--16",

editor = "Jaisie Sin and Edith Law and Jim Wallace and Cosmin Munteanu and Danai Korre",

booktitle = "CUI '25",

publisher = "Association for Computing Machinery",

address = "United States",

note = "7th ACM Conference on Conversational User Interfaces (CUI 2025) ; Conference date: 08-07-2025 Through 10-07-2025",

url = "https://cui.acm.org/2025/",

}

Liang, M, Wang, J & Luo, Y 2025, SmartEats: Investigating the Effects of Customizable Conversational Agent in Dietary Recommendations. in J Sin, E Law, J Wallace, C Munteanu & D Korre (eds), CUI '25: Proceedings of the 7th ACM Conference on Conversational User Interfaces., 63, Association for Computing Machinery, pp. 1-16, 7th ACM Conference on Conversational User Interfaces (CUI 2025), Waterloo, Ontario, Canada, 8/07/25. https://doi.org/10.1145/3719160.3736635

SmartEats: Investigating the Effects of Customizable Conversational Agent in Dietary Recommendations. / Liang, Minhui; Wang, Jinping; Luo, Yuhan.
CUI '25: Proceedings of the 7th ACM Conference on Conversational User Interfaces. ed. / Jaisie Sin; Edith Law; Jim Wallace; Cosmin Munteanu; Danai Korre. Association for Computing Machinery, 2025. p. 1-16 63.

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

TY - GEN

T1 - SmartEats

T2 - 7th ACM Conference on Conversational User Interfaces (CUI 2025)

AU - Liang, Minhui

AU - Wang, Jinping

AU - Luo, Yuhan

PY - 2025/7

Y1 - 2025/7

N2 - In conversational recommender systems (CRS), the communication characteristics exhibited by the conversational agent (CA) can greatly shape user experience and their perceptions of the recommendation quality. Yet, prior work often adopts a one-size-fits-all approach, leaving the potential benefits of CA customizability—allowing users to tailor agent traits to their preferences—largely unexplored. We examine this gap in the context of dietary recommendations by introducing SmartEats, a CRS featuring a CA that can be customized by users. Through a between-subjects experiment (N = 214), we compared SmartEats to a non-customizable baseline, and followed up with participants after one week to understand whether and how the recommendations affect their food choices. We found that CA customizability directly improved participants’ immediate experience and indirectly enhanced their ability to later recall the recommendations. Reflecting on the findings, we discuss opportunities for CRS to enhance health and well-being by leveraging the customizability of emerging AI technologies. © 2025 Copyright held by the owner/author(s).

AB - In conversational recommender systems (CRS), the communication characteristics exhibited by the conversational agent (CA) can greatly shape user experience and their perceptions of the recommendation quality. Yet, prior work often adopts a one-size-fits-all approach, leaving the potential benefits of CA customizability—allowing users to tailor agent traits to their preferences—largely unexplored. We examine this gap in the context of dietary recommendations by introducing SmartEats, a CRS featuring a CA that can be customized by users. Through a between-subjects experiment (N = 214), we compared SmartEats to a non-customizable baseline, and followed up with participants after one week to understand whether and how the recommendations affect their food choices. We found that CA customizability directly improved participants’ immediate experience and indirectly enhanced their ability to later recall the recommendations. Reflecting on the findings, we discuss opportunities for CRS to enhance health and well-being by leveraging the customizability of emerging AI technologies. © 2025 Copyright held by the owner/author(s).

KW - conversational recommender system

KW - large language model

KW - dietary recommendation

KW - health behavior

UR - https://www.scopus.com/pages/publications/105011626815

UR - https://www.scopus.com/pages/publications/105011626815#tab=impact

U2 - 10.1145/3719160.3736635

DO - 10.1145/3719160.3736635

M3 - RGC 32 - Refereed conference paper (with host publication)

SN - 9798400715273

SP - 1

EP - 16

BT - CUI '25

A2 - Sin, Jaisie

A2 - Law, Edith

A2 - Wallace, Jim

A2 - Munteanu, Cosmin

A2 - Korre, Danai

PB - Association for Computing Machinery

Y2 - 8 July 2025 through 10 July 2025

ER -

SmartEats: Investigating the Effects of Customizable Conversational Agent in Dietary Recommendations

Abstract

Conference

Funding

Research Keywords

Access Output

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

DON_RMG: Making Sense of Personal Health Data Leveraging Large Language Models - RMGS

Cite this

SmartEats: Investigating the Effects of Customizable Conversational Agent in Dietary Recommendations

Abstract

Conference

Funding

Research Keywords

Access Output

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

Projects

DON_RMG: Making Sense of Personal Health Data Leveraging Large Language Models - RMGS

Cite this