Ah, Alright, Okay! Communicating Understanding in Conversational Product Search
(2023) CUI '23: ACM conference on Conversational User Interfaces p.1-5- Abstract
- When talking about products, people often express their needs in vague terms with vocabulary that does not necessarily overlap with product descriptions written by retailers. This poses a problem for chatbots in online shops, as the vagueness and vocabulary mismatch can lead to misunderstandings. In human-human communication, people intuitively build a common understanding throughout a conversation, e.g., via feedback loops. To inform the design of conversational product search systems, we investigated the effect of different feedback behaviors on users’ perception of a chatbot’s competence and conversational engagement. Our results show that rephrasing the user’s input to express what was understood increases conversational engagement and... (More)
- When talking about products, people often express their needs in vague terms with vocabulary that does not necessarily overlap with product descriptions written by retailers. This poses a problem for chatbots in online shops, as the vagueness and vocabulary mismatch can lead to misunderstandings. In human-human communication, people intuitively build a common understanding throughout a conversation, e.g., via feedback loops. To inform the design of conversational product search systems, we investigated the effect of different feedback behaviors on users’ perception of a chatbot’s competence and conversational engagement. Our results show that rephrasing the user’s input to express what was understood increases conversational engagement and gives the impression of a competent chatbot. Using a generic feedback acknowledgment (e.g., “right” or “okay”), however, does not increase engagement or perceived competence. Auto-feedback for conversational product search systems therefore needs to be designed with care. (Less)
Please use this url to cite or link to this publication:
https://lup.lub.lu.se/record/d834ce1e-93d6-4197-a6b4-8b0e90d84b4d
- author
- Papenmeier, Andrea and Topp, Elin A. LU
- organization
- publishing date
- 2023-07
- type
- Chapter in Book/Report/Conference proceeding
- publication status
- published
- subject
- host publication
- Proceedings of the 5th International Conference on Conversational User Interfaces : CUI '23 - CUI '23
- article number
- 49
- pages
- 5 pages
- publisher
- Association for Computing Machinery (ACM)
- conference name
- CUI '23: ACM conference on Conversational User Interfaces
- conference location
- Eindhoven, Netherlands
- conference dates
- 2023-07-19 - 2023-07-21
- external identifiers
-
- scopus:85167833356
- DOI
- 10.1145/3571884.3604318
- language
- English
- LU publication?
- yes
- id
- d834ce1e-93d6-4197-a6b4-8b0e90d84b4d
- date added to LUP
- 2023-07-26 10:56:04
- date last changed
- 2023-11-22 22:32:24
@inproceedings{d834ce1e-93d6-4197-a6b4-8b0e90d84b4d, abstract = {{When talking about products, people often express their needs in vague terms with vocabulary that does not necessarily overlap with product descriptions written by retailers. This poses a problem for chatbots in online shops, as the vagueness and vocabulary mismatch can lead to misunderstandings. In human-human communication, people intuitively build a common understanding throughout a conversation, e.g., via feedback loops. To inform the design of conversational product search systems, we investigated the effect of different feedback behaviors on users’ perception of a chatbot’s competence and conversational engagement. Our results show that rephrasing the user’s input to express what was understood increases conversational engagement and gives the impression of a competent chatbot. Using a generic feedback acknowledgment (e.g., “right” or “okay”), however, does not increase engagement or perceived competence. Auto-feedback for conversational product search systems therefore needs to be designed with care.}}, author = {{Papenmeier, Andrea and Topp, Elin A.}}, booktitle = {{Proceedings of the 5th International Conference on Conversational User Interfaces : CUI '23}}, language = {{eng}}, pages = {{1--5}}, publisher = {{Association for Computing Machinery (ACM)}}, title = {{Ah, Alright, Okay! Communicating Understanding in Conversational Product Search}}, url = {{http://dx.doi.org/10.1145/3571884.3604318}}, doi = {{10.1145/3571884.3604318}}, year = {{2023}}, }