Eliciting User Food Preferences in terms of Taste and Texture in Spoken Dialogue Systems

Jie Zeng; Yukiko I. Nakano; Takeshi Morita; Ichiro Kobayashi; Takahira Yamaguchi

doi:10.1145/3279954.3279959

Eliciting User Food Preferences in terms of Taste and Texture in Spoken Dialogue Systems

Jie Zeng, Yukiko I. Nakano, Takeshi Morita, Ichiro Kobayashi, Takahira Yamaguchi

Department of Industrial and Systems Engineering

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

6 Citations (Scopus)

Abstract

Food preference varies from person to person and is not easy to verbalize. This study proposes a dialogue system that elicits the user’s food preference through human-robot interaction. First, as the default knowledge of the dialogue system, we determined the ingredients of each dish from a large-scale recipe database, and collected the taste and texture of each dish and its ingredients by analyzing a large number of Twitter messages. Subsequently, the dialogue system asks questions to elicit the user’s preferred taste/texture of the food by using the default knowledge base, while employing frame-based dialogue management. Finally, we created a food vector space that represents the relationship between the dish names, ingredients, and taste/texture expressions. We also discuss the possibility of using this vector space in dish recommendation.

Original language	English
Title of host publication	MHFI 2018 - 3rd Workshop on Multisensory Approaches to Human-Food Interaction
Editors	Carlos Velasco, Anton Nijholt, Marianna Obrist, Katsunori Okajima, Charles Spence
Publisher	Association for Computing Machinery, Inc
ISBN (Electronic)	9781450360746
DOIs	https://doi.org/10.1145/3279954.3279959
Publication status	Published - 2018 Oct 16
Event	3rd Workshop on Multisensory Approaches to Human-Food Interaction, MHFI 2018, in conjunction with the 20th ACM International Conference on Multimodal Interaction, ICMI 2018 - Boulder, United States Duration: 2018 Oct 16 → …

Publication series

Name	MHFI 2018 - 3rd Workshop on Multisensory Approaches to Human-Food Interaction

Other

Other	3rd Workshop on Multisensory Approaches to Human-Food Interaction, MHFI 2018, in conjunction with the 20th ACM International Conference on Multimodal Interaction, ICMI 2018
Country/Territory	United States
City	Boulder
Period	18/10/16 → …

Keywords

Spoken dialogue system
Taste and texture
Twitter

ASJC Scopus subject areas

Hardware and Architecture
Food Science
Social Psychology
Computer Science Applications
Computer Vision and Pattern Recognition
Cultural Studies
Human-Computer Interaction

Access to Document

10.1145/3279954.3279959

Cite this

Zeng, J., Nakano, Y. I., Morita, T., Kobayashi, I., & Yamaguchi, T. (2018). Eliciting User Food Preferences in terms of Taste and Texture in Spoken Dialogue Systems. In C. Velasco, A. Nijholt, M. Obrist, K. Okajima, & C. Spence (Eds.), MHFI 2018 - 3rd Workshop on Multisensory Approaches to Human-Food Interaction (MHFI 2018 - 3rd Workshop on Multisensory Approaches to Human-Food Interaction). Association for Computing Machinery, Inc. https://doi.org/10.1145/3279954.3279959

Eliciting User Food Preferences in terms of Taste and Texture in Spoken Dialogue Systems. / Zeng, Jie; Nakano, Yukiko I.; Morita, Takeshi et al.
MHFI 2018 - 3rd Workshop on Multisensory Approaches to Human-Food Interaction. ed. / Carlos Velasco; Anton Nijholt; Marianna Obrist; Katsunori Okajima; Charles Spence. Association for Computing Machinery, Inc, 2018. (MHFI 2018 - 3rd Workshop on Multisensory Approaches to Human-Food Interaction).

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

Zeng, J, Nakano, YI, Morita, T, Kobayashi, I & Yamaguchi, T 2018, Eliciting User Food Preferences in terms of Taste and Texture in Spoken Dialogue Systems. in C Velasco, A Nijholt, M Obrist, K Okajima & C Spence (eds), MHFI 2018 - 3rd Workshop on Multisensory Approaches to Human-Food Interaction. MHFI 2018 - 3rd Workshop on Multisensory Approaches to Human-Food Interaction, Association for Computing Machinery, Inc, 3rd Workshop on Multisensory Approaches to Human-Food Interaction, MHFI 2018, in conjunction with the 20th ACM International Conference on Multimodal Interaction, ICMI 2018, Boulder, United States, 18/10/16. https://doi.org/10.1145/3279954.3279959

Zeng J, Nakano YI, Morita T, Kobayashi I, Yamaguchi T. Eliciting User Food Preferences in terms of Taste and Texture in Spoken Dialogue Systems. In Velasco C, Nijholt A, Obrist M, Okajima K, Spence C, editors, MHFI 2018 - 3rd Workshop on Multisensory Approaches to Human-Food Interaction. Association for Computing Machinery, Inc. 2018. (MHFI 2018 - 3rd Workshop on Multisensory Approaches to Human-Food Interaction). doi: 10.1145/3279954.3279959

Zeng, Jie ; Nakano, Yukiko I. ; Morita, Takeshi et al. / Eliciting User Food Preferences in terms of Taste and Texture in Spoken Dialogue Systems. MHFI 2018 - 3rd Workshop on Multisensory Approaches to Human-Food Interaction. editor / Carlos Velasco ; Anton Nijholt ; Marianna Obrist ; Katsunori Okajima ; Charles Spence. Association for Computing Machinery, Inc, 2018. (MHFI 2018 - 3rd Workshop on Multisensory Approaches to Human-Food Interaction).

@inproceedings{aa0e3180ff9f43df8b5b85514b531d1c,

title = "Eliciting User Food Preferences in terms of Taste and Texture in Spoken Dialogue Systems",

abstract = "Food preference varies from person to person and is not easy to verbalize. This study proposes a dialogue system that elicits the user{\textquoteright}s food preference through human-robot interaction. First, as the default knowledge of the dialogue system, we determined the ingredients of each dish from a large-scale recipe database, and collected the taste and texture of each dish and its ingredients by analyzing a large number of Twitter messages. Subsequently, the dialogue system asks questions to elicit the user{\textquoteright}s preferred taste/texture of the food by using the default knowledge base, while employing frame-based dialogue management. Finally, we created a food vector space that represents the relationship between the dish names, ingredients, and taste/texture expressions. We also discuss the possibility of using this vector space in dish recommendation.",

keywords = "Spoken dialogue system, Taste and texture, Twitter",

author = "Jie Zeng and Nakano, {Yukiko I.} and Takeshi Morita and Ichiro Kobayashi and Takahira Yamaguchi",

note = "Funding Information: This work was supported by CREST, JST. Publisher Copyright: {\textcopyright} 2018 Association for Computing Machinery.; 3rd Workshop on Multisensory Approaches to Human-Food Interaction, MHFI 2018, in conjunction with the 20th ACM International Conference on Multimodal Interaction, ICMI 2018 ; Conference date: 16-10-2018",

year = "2018",

month = oct,

day = "16",

doi = "10.1145/3279954.3279959",

language = "English",

series = "MHFI 2018 - 3rd Workshop on Multisensory Approaches to Human-Food Interaction",

publisher = "Association for Computing Machinery, Inc",

editor = "Carlos Velasco and Anton Nijholt and Marianna Obrist and Katsunori Okajima and Charles Spence",

booktitle = "MHFI 2018 - 3rd Workshop on Multisensory Approaches to Human-Food Interaction",

}

TY - GEN

T1 - Eliciting User Food Preferences in terms of Taste and Texture in Spoken Dialogue Systems

AU - Zeng, Jie

AU - Nakano, Yukiko I.

AU - Morita, Takeshi

AU - Kobayashi, Ichiro

AU - Yamaguchi, Takahira

PY - 2018/10/16

Y1 - 2018/10/16

N2 - Food preference varies from person to person and is not easy to verbalize. This study proposes a dialogue system that elicits the user’s food preference through human-robot interaction. First, as the default knowledge of the dialogue system, we determined the ingredients of each dish from a large-scale recipe database, and collected the taste and texture of each dish and its ingredients by analyzing a large number of Twitter messages. Subsequently, the dialogue system asks questions to elicit the user’s preferred taste/texture of the food by using the default knowledge base, while employing frame-based dialogue management. Finally, we created a food vector space that represents the relationship between the dish names, ingredients, and taste/texture expressions. We also discuss the possibility of using this vector space in dish recommendation.

AB - Food preference varies from person to person and is not easy to verbalize. This study proposes a dialogue system that elicits the user’s food preference through human-robot interaction. First, as the default knowledge of the dialogue system, we determined the ingredients of each dish from a large-scale recipe database, and collected the taste and texture of each dish and its ingredients by analyzing a large number of Twitter messages. Subsequently, the dialogue system asks questions to elicit the user’s preferred taste/texture of the food by using the default knowledge base, while employing frame-based dialogue management. Finally, we created a food vector space that represents the relationship between the dish names, ingredients, and taste/texture expressions. We also discuss the possibility of using this vector space in dish recommendation.

KW - Spoken dialogue system

KW - Taste and texture

KW - Twitter

UR - http://www.scopus.com/inward/record.url?scp=85056655745&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85056655745&partnerID=8YFLogxK

U2 - 10.1145/3279954.3279959

DO - 10.1145/3279954.3279959

M3 - Conference contribution

AN - SCOPUS:85056655745

T3 - MHFI 2018 - 3rd Workshop on Multisensory Approaches to Human-Food Interaction

BT - MHFI 2018 - 3rd Workshop on Multisensory Approaches to Human-Food Interaction

A2 - Velasco, Carlos

A2 - Nijholt, Anton

A2 - Obrist, Marianna

A2 - Okajima, Katsunori

A2 - Spence, Charles

PB - Association for Computing Machinery, Inc

T2 - 3rd Workshop on Multisensory Approaches to Human-Food Interaction, MHFI 2018, in conjunction with the 20th ACM International Conference on Multimodal Interaction, ICMI 2018

Y2 - 16 October 2018

ER -

Eliciting User Food Preferences in terms of Taste and Texture in Spoken Dialogue Systems

Abstract

Publication series

Other

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this