Back to the Future: Lessons from Knowledge Engineering Methodologies for Chatbot Design and Development

Gillian Cameron, David Cameron, Gavin Megaw, RR Bond, Maurice Mulvenna, Siobhan O'Neill, C Armour, Michael McTear

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

This paper explores the area of conversational user interfaces and chatbot development, focusing on the methodological aspects of development. The domain in this paper for chatbot development is healthcare. An increasing issue in chatbot development relates to the difficulty in eliciting specific domain knowledge. As chatbots become more ubiquitous in our daily lives with more complex use cases, the process of eliciting and codifying the domain knowledge has become more complex. This is a problem revisited; in the 1980’s, ‘expert systems’ grew rapidly in popularity and such systems required the same processes of elicitation and codification of human know-how or expertise as we now re-witness in modern chatbot development. A new area of ‘knowledge engineering’ developed from the expert systems or ‘knowledge-based systems’ field and from this several knowledge engineering methodologies emerged. The present paper revisits these methodologies and asks if there are lessons to be learned for chatbot design and development from such decades old knowledge engineering methods. The paper presents an amendment to a chatbot methodology, incorporating new stages of ‘knowledge gathering’ and ‘usability testing’ into the process.
LanguageEnglish
Title of host publicationProceedings of the 32nd International BCS Human Computer Interaction Conference (HCI-2018)
EditorsRaymond Bond, Maurice Mulvenna, Jonathan Wallace, Michaela Black
Place of PublicationSwindon, UK
Number of pages5
DOIs
Publication statusPublished - 10 May 2018
EventBritish HCI Conference 2018 - Belfast, Belfast, Northern Ireland
Duration: 2 Jul 20186 Jul 2018

Conference

ConferenceBritish HCI Conference 2018
Abbreviated titleBHCI2018
CountryNorthern Ireland
CityBelfast
Period2/07/186/07/18

Fingerprint

Knowledge engineering
Expert systems
Knowledge based systems
User interfaces
Testing

Keywords

  • AI
  • chatbots
  • knowledge engineering

Cite this

Cameron, G., Cameron, D., Megaw, G., Bond, RR., Mulvenna, M., O'Neill, S., ... McTear, M. (2018). Back to the Future: Lessons from Knowledge Engineering Methodologies for Chatbot Design and Development. In R. Bond, M. Mulvenna, J. Wallace, & M. Black (Eds.), Proceedings of the 32nd International BCS Human Computer Interaction Conference (HCI-2018) Swindon, UK. https://doi.org/10.14236/ewic/HCI2018.153
Cameron, Gillian ; Cameron, David ; Megaw, Gavin ; Bond, RR ; Mulvenna, Maurice ; O'Neill, Siobhan ; Armour, C ; McTear, Michael. / Back to the Future: Lessons from Knowledge Engineering Methodologies for Chatbot Design and Development. Proceedings of the 32nd International BCS Human Computer Interaction Conference (HCI-2018). editor / Raymond Bond ; Maurice Mulvenna ; Jonathan Wallace ; Michaela Black. Swindon, UK, 2018.
@inproceedings{df5f727d3fc84c9ba9abac2cade8ab69,
title = "Back to the Future: Lessons from Knowledge Engineering Methodologies for Chatbot Design and Development",
abstract = "This paper explores the area of conversational user interfaces and chatbot development, focusing on the methodological aspects of development. The domain in this paper for chatbot development is healthcare. An increasing issue in chatbot development relates to the difficulty in eliciting specific domain knowledge. As chatbots become more ubiquitous in our daily lives with more complex use cases, the process of eliciting and codifying the domain knowledge has become more complex. This is a problem revisited; in the 1980’s, ‘expert systems’ grew rapidly in popularity and such systems required the same processes of elicitation and codification of human know-how or expertise as we now re-witness in modern chatbot development. A new area of ‘knowledge engineering’ developed from the expert systems or ‘knowledge-based systems’ field and from this several knowledge engineering methodologies emerged. The present paper revisits these methodologies and asks if there are lessons to be learned for chatbot design and development from such decades old knowledge engineering methods. The paper presents an amendment to a chatbot methodology, incorporating new stages of ‘knowledge gathering’ and ‘usability testing’ into the process.",
keywords = "AI, chatbots, knowledge engineering",
author = "Gillian Cameron and David Cameron and Gavin Megaw and RR Bond and Maurice Mulvenna and Siobhan O'Neill and C Armour and Michael McTear",
year = "2018",
month = "5",
day = "10",
doi = "http://dx.doi.org/10.14236/ewic/HCI2018.153",
language = "English",
editor = "Raymond Bond and Maurice Mulvenna and Jonathan Wallace and Michaela Black",
booktitle = "Proceedings of the 32nd International BCS Human Computer Interaction Conference (HCI-2018)",

}

Cameron, G, Cameron, D, Megaw, G, Bond, RR, Mulvenna, M, O'Neill, S, Armour, C & McTear, M 2018, Back to the Future: Lessons from Knowledge Engineering Methodologies for Chatbot Design and Development. in R Bond, M Mulvenna, J Wallace & M Black (eds), Proceedings of the 32nd International BCS Human Computer Interaction Conference (HCI-2018). Swindon, UK, British HCI Conference 2018, Belfast, Northern Ireland, 2/07/18. https://doi.org/10.14236/ewic/HCI2018.153

Back to the Future: Lessons from Knowledge Engineering Methodologies for Chatbot Design and Development. / Cameron, Gillian; Cameron, David; Megaw, Gavin; Bond, RR; Mulvenna, Maurice; O'Neill, Siobhan; Armour, C; McTear, Michael.

Proceedings of the 32nd International BCS Human Computer Interaction Conference (HCI-2018). ed. / Raymond Bond; Maurice Mulvenna; Jonathan Wallace; Michaela Black. Swindon, UK, 2018.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Back to the Future: Lessons from Knowledge Engineering Methodologies for Chatbot Design and Development

AU - Cameron, Gillian

AU - Cameron, David

AU - Megaw, Gavin

AU - Bond, RR

AU - Mulvenna, Maurice

AU - O'Neill, Siobhan

AU - Armour, C

AU - McTear, Michael

PY - 2018/5/10

Y1 - 2018/5/10

N2 - This paper explores the area of conversational user interfaces and chatbot development, focusing on the methodological aspects of development. The domain in this paper for chatbot development is healthcare. An increasing issue in chatbot development relates to the difficulty in eliciting specific domain knowledge. As chatbots become more ubiquitous in our daily lives with more complex use cases, the process of eliciting and codifying the domain knowledge has become more complex. This is a problem revisited; in the 1980’s, ‘expert systems’ grew rapidly in popularity and such systems required the same processes of elicitation and codification of human know-how or expertise as we now re-witness in modern chatbot development. A new area of ‘knowledge engineering’ developed from the expert systems or ‘knowledge-based systems’ field and from this several knowledge engineering methodologies emerged. The present paper revisits these methodologies and asks if there are lessons to be learned for chatbot design and development from such decades old knowledge engineering methods. The paper presents an amendment to a chatbot methodology, incorporating new stages of ‘knowledge gathering’ and ‘usability testing’ into the process.

AB - This paper explores the area of conversational user interfaces and chatbot development, focusing on the methodological aspects of development. The domain in this paper for chatbot development is healthcare. An increasing issue in chatbot development relates to the difficulty in eliciting specific domain knowledge. As chatbots become more ubiquitous in our daily lives with more complex use cases, the process of eliciting and codifying the domain knowledge has become more complex. This is a problem revisited; in the 1980’s, ‘expert systems’ grew rapidly in popularity and such systems required the same processes of elicitation and codification of human know-how or expertise as we now re-witness in modern chatbot development. A new area of ‘knowledge engineering’ developed from the expert systems or ‘knowledge-based systems’ field and from this several knowledge engineering methodologies emerged. The present paper revisits these methodologies and asks if there are lessons to be learned for chatbot design and development from such decades old knowledge engineering methods. The paper presents an amendment to a chatbot methodology, incorporating new stages of ‘knowledge gathering’ and ‘usability testing’ into the process.

KW - AI

KW - chatbots

KW - knowledge engineering

UR - https://dl.acm.org/citation.cfm?id=3301173

UR - https://ewic.bcs.org/upload/pdf/ewic_hci18_wip_paper63.pdf

U2 - http://dx.doi.org/10.14236/ewic/HCI2018.153

DO - http://dx.doi.org/10.14236/ewic/HCI2018.153

M3 - Conference contribution

BT - Proceedings of the 32nd International BCS Human Computer Interaction Conference (HCI-2018)

A2 - Bond, Raymond

A2 - Mulvenna, Maurice

A2 - Wallace, Jonathan

A2 - Black, Michaela

CY - Swindon, UK

ER -

Cameron G, Cameron D, Megaw G, Bond RR, Mulvenna M, O'Neill S et al. Back to the Future: Lessons from Knowledge Engineering Methodologies for Chatbot Design and Development. In Bond R, Mulvenna M, Wallace J, Black M, editors, Proceedings of the 32nd International BCS Human Computer Interaction Conference (HCI-2018). Swindon, UK. 2018 https://doi.org/10.14236/ewic/HCI2018.153