A model of social explanations for a conversational movie recommendation system

Florian Pecune; Shruti Murali; Vivian Tsai; Yoichi Matsuyama; Justine Cassell

doi:10.1145/3349537.3351899

A model of social explanations for a conversational movie recommendation system

Florian Pecune, Shruti Murali, Vivian Tsai, Yoichi Matsuyama, Justine Cassell

Green Computing Systems Research Organization

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

5 Citations (Scopus)

Abstract

A critical aspect of any recommendation process is explaining the reasoning behind each recommendation. These explanations can not only improve users' experiences, but also change their perception of the recommendation quality. This work describes our human-centered design for our conversational movie recommendation agent, which explains its decisions as humans would. After exploring and analyzing a corpus of dyadic interactions, we developed a computational model of explanations. We then incorporated this model in the architecture of a conversational agent and evaluated the resulting system via a user experiment. Our results show that social explanations can improve the perceived quality of both the system and the interaction, regardless of the intrinsic quality of the recommendations.

Original language	English
Title of host publication	HAI 2019 - Proceedings of the 7th International Conference on Human-Agent Interaction
Publisher	Association for Computing Machinery, Inc
Pages	135-143
Number of pages	9
ISBN (Electronic)	9781450369220
DOIs	https://doi.org/10.1145/3349537.3351899
Publication status	Published - 2019 Sep 25
Event	7th International Conference on Human-Agent Interaction, HAI 2019 - Kyoto, Japan Duration: 2019 Oct 6 → 2019 Oct 10

Publication series

Name	HAI 2019 - Proceedings of the 7th International Conference on Human-Agent Interaction

Conference

Conference	7th International Conference on Human-Agent Interaction, HAI 2019
Country	Japan
City	Kyoto
Period	19/10/6 → 19/10/10

Keywords

Conversational recommendation system
Explanation
Socially-aware

ASJC Scopus subject areas

Artificial Intelligence
Human-Computer Interaction
Software

Access to Document

10.1145/3349537.3351899

Fingerprint Dive into the research topics of 'A model of social explanations for a conversational movie recommendation system'. Together they form a unique fingerprint.

Cite this

Pecune, F., Murali, S., Tsai, V., Matsuyama, Y., & Cassell, J. (2019). A model of social explanations for a conversational movie recommendation system. In HAI 2019 - Proceedings of the 7th International Conference on Human-Agent Interaction (pp. 135-143). (HAI 2019 - Proceedings of the 7th International Conference on Human-Agent Interaction). Association for Computing Machinery, Inc. https://doi.org/10.1145/3349537.3351899

A model of social explanations for a conversational movie recommendation system. / Pecune, Florian; Murali, Shruti; Tsai, Vivian; Matsuyama, Yoichi; Cassell, Justine.

HAI 2019 - Proceedings of the 7th International Conference on Human-Agent Interaction. Association for Computing Machinery, Inc, 2019. p. 135-143 (HAI 2019 - Proceedings of the 7th International Conference on Human-Agent Interaction).

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

Pecune, F, Murali, S, Tsai, V, Matsuyama, Y & Cassell, J 2019, A model of social explanations for a conversational movie recommendation system. in HAI 2019 - Proceedings of the 7th International Conference on Human-Agent Interaction. HAI 2019 - Proceedings of the 7th International Conference on Human-Agent Interaction, Association for Computing Machinery, Inc, pp. 135-143, 7th International Conference on Human-Agent Interaction, HAI 2019, Kyoto, Japan, 19/10/6. https://doi.org/10.1145/3349537.3351899

Pecune F, Murali S, Tsai V, Matsuyama Y, Cassell J. A model of social explanations for a conversational movie recommendation system. In HAI 2019 - Proceedings of the 7th International Conference on Human-Agent Interaction. Association for Computing Machinery, Inc. 2019. p. 135-143. (HAI 2019 - Proceedings of the 7th International Conference on Human-Agent Interaction). https://doi.org/10.1145/3349537.3351899

Pecune, Florian ; Murali, Shruti ; Tsai, Vivian ; Matsuyama, Yoichi ; Cassell, Justine. / A model of social explanations for a conversational movie recommendation system. HAI 2019 - Proceedings of the 7th International Conference on Human-Agent Interaction. Association for Computing Machinery, Inc, 2019. pp. 135-143 (HAI 2019 - Proceedings of the 7th International Conference on Human-Agent Interaction).

@inproceedings{5f2b21489dc84a16b1ec8dd54ac3e819,

title = "A model of social explanations for a conversational movie recommendation system",

abstract = "A critical aspect of any recommendation process is explaining the reasoning behind each recommendation. These explanations can not only improve users' experiences, but also change their perception of the recommendation quality. This work describes our human-centered design for our conversational movie recommendation agent, which explains its decisions as humans would. After exploring and analyzing a corpus of dyadic interactions, we developed a computational model of explanations. We then incorporated this model in the architecture of a conversational agent and evaluated the resulting system via a user experiment. Our results show that social explanations can improve the perceived quality of both the system and the interaction, regardless of the intrinsic quality of the recommendations.",

keywords = "Conversational recommendation system, Explanation, Socially-aware",

author = "Florian Pecune and Shruti Murali and Vivian Tsai and Yoichi Matsuyama and Justine Cassell",

note = "Funding Information: This work was supported in part by funding from Oath and the IT R&D program of MSIP/IITP [2017-0-00255, Autonomous digital companion development]. We would also like to thank John Choi for his generous help, Yoo Jin Shin for refining annotations, and the members of Carnegie Mellon University{\textquoteright}s ArticuLab for their feedback and support.; 7th International Conference on Human-Agent Interaction, HAI 2019 ; Conference date: 06-10-2019 Through 10-10-2019",

year = "2019",

month = sep,

day = "25",

doi = "10.1145/3349537.3351899",

language = "English",

series = "HAI 2019 - Proceedings of the 7th International Conference on Human-Agent Interaction",

publisher = "Association for Computing Machinery, Inc",

pages = "135--143",

booktitle = "HAI 2019 - Proceedings of the 7th International Conference on Human-Agent Interaction",

}

TY - GEN

T1 - A model of social explanations for a conversational movie recommendation system

AU - Pecune, Florian

AU - Murali, Shruti

AU - Tsai, Vivian

AU - Matsuyama, Yoichi

AU - Cassell, Justine

N1 - Funding Information: This work was supported in part by funding from Oath and the IT R&D program of MSIP/IITP [2017-0-00255, Autonomous digital companion development]. We would also like to thank John Choi for his generous help, Yoo Jin Shin for refining annotations, and the members of Carnegie Mellon University’s ArticuLab for their feedback and support.

PY - 2019/9/25

Y1 - 2019/9/25

N2 - A critical aspect of any recommendation process is explaining the reasoning behind each recommendation. These explanations can not only improve users' experiences, but also change their perception of the recommendation quality. This work describes our human-centered design for our conversational movie recommendation agent, which explains its decisions as humans would. After exploring and analyzing a corpus of dyadic interactions, we developed a computational model of explanations. We then incorporated this model in the architecture of a conversational agent and evaluated the resulting system via a user experiment. Our results show that social explanations can improve the perceived quality of both the system and the interaction, regardless of the intrinsic quality of the recommendations.

AB - A critical aspect of any recommendation process is explaining the reasoning behind each recommendation. These explanations can not only improve users' experiences, but also change their perception of the recommendation quality. This work describes our human-centered design for our conversational movie recommendation agent, which explains its decisions as humans would. After exploring and analyzing a corpus of dyadic interactions, we developed a computational model of explanations. We then incorporated this model in the architecture of a conversational agent and evaluated the resulting system via a user experiment. Our results show that social explanations can improve the perceived quality of both the system and the interaction, regardless of the intrinsic quality of the recommendations.

KW - Conversational recommendation system

KW - Explanation

KW - Socially-aware

UR - http://www.scopus.com/inward/record.url?scp=85077120890&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85077120890&partnerID=8YFLogxK

U2 - 10.1145/3349537.3351899

DO - 10.1145/3349537.3351899

M3 - Conference contribution

AN - SCOPUS:85077120890

T3 - HAI 2019 - Proceedings of the 7th International Conference on Human-Agent Interaction

SP - 135

EP - 143

BT - HAI 2019 - Proceedings of the 7th International Conference on Human-Agent Interaction

PB - Association for Computing Machinery, Inc

T2 - 7th International Conference on Human-Agent Interaction, HAI 2019

Y2 - 6 October 2019 through 10 October 2019

ER -