Towards a taxonomy of user feedback intents for conversational recommendations

Wanling Cai; Li Chen

Towards a taxonomy of user feedback intents for conversational recommendations

Wanling Cai, Li Chen

Department of Computer Science

Research output: Chapter in book/report/conference proceeding › Conference proceeding › peer-review

7 Citations (Scopus)

Abstract

Understanding users’ feedback on recommendation in natural language is crucially important for assisting the system to refine its understanding of the user’s preferences and provide more accurate recommendations in the subsequent interactions. In this paper, we report the results of an exploratory study on a human-human dialogue dataset centered around movie recommendations. In particular, we manually labeled a set of over 200 dialogues at the utterance level, and then conducted descriptive analysis on them from both seekers’ and recommenders’ perspectives. The results reveal not only seekers’ feedback intents as well as the types of preferences they have expressed, but also the reactions of human recommenders that have finally led to successful recommendation. A taxonomy for feedback intents is established along with the results, which could be constructive for improving conversational recommender systems.

Original language	English
Title of host publication	Proceedings of ACM RecSys 2019 Late-breaking Results, co-located with the 13th ACM Conference on Recommender Systems (RecSys 2019)
Editors	Marko Tkalcic, Sole Pera
Publisher	CEUR-WS
Pages	51-55
Number of pages	5
Publication status	Published - 26 Aug 2019
Event	2019 ACM Conference on Recommender Systems Late-breaking Results, ACM RecSys LBR 2019 - Copenhagen, Denmark Duration: 16 Sept 2019 → 20 Sept 2019 https://ceur-ws.org/Vol-2431/

Publication series

Name	CEUR Workshop Proceedings
Publisher	CEUR-WS
Volume	2431
ISSN (Print)	1613-0073

Conference

Conference	2019 ACM Conference on Recommender Systems Late-breaking Results, ACM RecSys LBR 2019
Country/Territory	Denmark
City	Copenhagen
Period	16/09/19 → 20/09/19
Internet address	https://ceur-ws.org/Vol-2431/

User-Defined Keywords

Dialogue-based conversational recommender systems
Intent taxonomy
User feedback

Access to Document

http://ceur-ws.org/Vol-2431/paper11.pdf

Cite this

Cai, W., & Chen, L. (2019). Towards a taxonomy of user feedback intents for conversational recommendations. In M. Tkalcic, & S. Pera (Eds.), Proceedings of ACM RecSys 2019 Late-breaking Results, co-located with the 13th ACM Conference on Recommender Systems (RecSys 2019) (pp. 51-55). (CEUR Workshop Proceedings; Vol. 2431). CEUR-WS. http://ceur-ws.org/Vol-2431/paper11.pdf

@inproceedings{225c83cb4426441f8a66456f1130236f,

title = "Towards a taxonomy of user feedback intents for conversational recommendations",

abstract = "Understanding users{\textquoteright} feedback on recommendation in natural language is crucially important for assisting the system to refine its understanding of the user{\textquoteright}s preferences and provide more accurate recommendations in the subsequent interactions. In this paper, we report the results of an exploratory study on a human-human dialogue dataset centered around movie recommendations. In particular, we manually labeled a set of over 200 dialogues at the utterance level, and then conducted descriptive analysis on them from both seekers{\textquoteright} and recommenders{\textquoteright} perspectives. The results reveal not only seekers{\textquoteright} feedback intents as well as the types of preferences they have expressed, but also the reactions of human recommenders that have finally led to successful recommendation. A taxonomy for feedback intents is established along with the results, which could be constructive for improving conversational recommender systems.",

keywords = "Dialogue-based conversational recommender systems, Intent taxonomy, User feedback",

author = "Wanling Cai and Li Chen",

note = "Publisher Copyright: Copyright {\textcopyright}2019 for this paper by its authors. Copyright: Copyright 2019 Elsevier B.V., All rights reserved.; 2019 ACM Conference on Recommender Systems Late-breaking Results, ACM RecSys LBR 2019 ; Conference date: 16-09-2019 Through 20-09-2019",

year = "2019",

month = aug,

day = "26",

language = "English",

series = "CEUR Workshop Proceedings",

publisher = "CEUR-WS",

pages = "51--55",

editor = "Marko Tkalcic and Sole Pera",

booktitle = "Proceedings of ACM RecSys 2019 Late-breaking Results, co-located with the 13th ACM Conference on Recommender Systems (RecSys 2019)",

url = "https://ceur-ws.org/Vol-2431/",

}

Cai, W & Chen, L 2019, Towards a taxonomy of user feedback intents for conversational recommendations. in M Tkalcic & S Pera (eds), Proceedings of ACM RecSys 2019 Late-breaking Results, co-located with the 13th ACM Conference on Recommender Systems (RecSys 2019). CEUR Workshop Proceedings, vol. 2431, CEUR-WS, pp. 51-55, 2019 ACM Conference on Recommender Systems Late-breaking Results, ACM RecSys LBR 2019, Copenhagen, Denmark, 16/09/19. <http://ceur-ws.org/Vol-2431/paper11.pdf>

Towards a taxonomy of user feedback intents for conversational recommendations. / Cai, Wanling; Chen, Li.
Proceedings of ACM RecSys 2019 Late-breaking Results, co-located with the 13th ACM Conference on Recommender Systems (RecSys 2019). ed. / Marko Tkalcic; Sole Pera. CEUR-WS, 2019. p. 51-55 (CEUR Workshop Proceedings; Vol. 2431).

Research output: Chapter in book/report/conference proceeding › Conference proceeding › peer-review

TY - GEN

T1 - Towards a taxonomy of user feedback intents for conversational recommendations

AU - Cai, Wanling

AU - Chen, Li

PY - 2019/8/26

Y1 - 2019/8/26

N2 - Understanding users’ feedback on recommendation in natural language is crucially important for assisting the system to refine its understanding of the user’s preferences and provide more accurate recommendations in the subsequent interactions. In this paper, we report the results of an exploratory study on a human-human dialogue dataset centered around movie recommendations. In particular, we manually labeled a set of over 200 dialogues at the utterance level, and then conducted descriptive analysis on them from both seekers’ and recommenders’ perspectives. The results reveal not only seekers’ feedback intents as well as the types of preferences they have expressed, but also the reactions of human recommenders that have finally led to successful recommendation. A taxonomy for feedback intents is established along with the results, which could be constructive for improving conversational recommender systems.

AB - Understanding users’ feedback on recommendation in natural language is crucially important for assisting the system to refine its understanding of the user’s preferences and provide more accurate recommendations in the subsequent interactions. In this paper, we report the results of an exploratory study on a human-human dialogue dataset centered around movie recommendations. In particular, we manually labeled a set of over 200 dialogues at the utterance level, and then conducted descriptive analysis on them from both seekers’ and recommenders’ perspectives. The results reveal not only seekers’ feedback intents as well as the types of preferences they have expressed, but also the reactions of human recommenders that have finally led to successful recommendation. A taxonomy for feedback intents is established along with the results, which could be constructive for improving conversational recommender systems.

KW - Dialogue-based conversational recommender systems

KW - Intent taxonomy

KW - User feedback

UR - http://ceur-ws.org/Vol-2431/

UR - http://www.scopus.com/inward/record.url?scp=85071754531&partnerID=8YFLogxK

M3 - Conference proceeding

AN - SCOPUS:85071754531

T3 - CEUR Workshop Proceedings

SP - 51

EP - 55

BT - Proceedings of ACM RecSys 2019 Late-breaking Results, co-located with the 13th ACM Conference on Recommender Systems (RecSys 2019)

A2 - Tkalcic, Marko

A2 - Pera, Sole

PB - CEUR-WS

T2 - 2019 ACM Conference on Recommender Systems Late-breaking Results, ACM RecSys LBR 2019

Y2 - 16 September 2019 through 20 September 2019

ER -

Towards a taxonomy of user feedback intents for conversational recommendations

Abstract

Publication series

Conference

User-Defined Keywords

Access to Document

Other files and links

Fingerprint

Cite this