Creating Humanlike Chatbots: What Chatbot Developers Could Learn From Webcare Employees In Adopting A Conversational Human Voice

C. Liebrecht, Charlotte van Hooijdonk

Research output: Contribution to conferencePaperScientificpeer-review

Abstract

Currently, conversations with chatbots are perceived as unnatural and
impersonal. One way to enhance the feeling of humanlike responses is by implementing an engaging communication style (i.e., Conversational Human Voice (CHV); Kelleher, 2009) which positively affects people’s perceptions of the organization. This communication style contributes to the effectiveness of online
communication between organizations and customers (i.e., webcare). This communication style is of high relevance to chatbot design and development. This project aimed to investigate how insights on the use of CHV in organizations’ messages and the perceptions of CHV can be implemented in customer service automation. A corpus study was conducted to investigate which linguistic elements are used in organizations’ messages. Subsequently, an experiment was conducted to assess to what extent linguistic elements contribute to the perception of CHV. Based on these two studies, we investigated whether the amount of CHV can be identified automatically. These findings could be used to design humanlike chatbots that use a natural and personal communication style like their human conversation partner.
Original languageEnglish
Number of pages15
Publication statusE-pub ahead of print - 20 Nov 2019
EventConversations 2019: 3rd international workshop on chatbot research - University of Amsterdam, Amsterdam, Netherlands
Duration: 19 Nov 201920 Nov 2019
https://conversations2019.wordpress.com/

Conference

ConferenceConversations 2019
CountryNetherlands
CityAmsterdam
Period19/11/1920/11/19
Internet address

Fingerprint

Employees
Developer
Communication style
Experiment
Customer service
Design and development
Automation

Keywords

  • Chatbots
  • Customer service
  • Strategie
  • Tone of voice
  • corporate communicatie
  • klantcontact

Cite this

Liebrecht, C., & van Hooijdonk, C. (2019). Creating Humanlike Chatbots: What Chatbot Developers Could Learn From Webcare Employees In Adopting A Conversational Human Voice. Paper presented at Conversations 2019, Amsterdam, Netherlands.
Liebrecht, C. ; van Hooijdonk, Charlotte. / Creating Humanlike Chatbots : What Chatbot Developers Could Learn From Webcare Employees In Adopting A Conversational Human Voice. Paper presented at Conversations 2019, Amsterdam, Netherlands.15 p.
@conference{af81a5bef4e442c6adf7711601c59d12,
title = "Creating Humanlike Chatbots: What Chatbot Developers Could Learn From Webcare Employees In Adopting A Conversational Human Voice",
abstract = "Currently, conversations with chatbots are perceived as unnatural andimpersonal. One way to enhance the feeling of humanlike responses is by implementing an engaging communication style (i.e., Conversational Human Voice (CHV); Kelleher, 2009) which positively affects people’s perceptions of the organization. This communication style contributes to the effectiveness of onlinecommunication between organizations and customers (i.e., webcare). This communication style is of high relevance to chatbot design and development. This project aimed to investigate how insights on the use of CHV in organizations’ messages and the perceptions of CHV can be implemented in customer service automation. A corpus study was conducted to investigate which linguistic elements are used in organizations’ messages. Subsequently, an experiment was conducted to assess to what extent linguistic elements contribute to the perception of CHV. Based on these two studies, we investigated whether the amount of CHV can be identified automatically. These findings could be used to design humanlike chatbots that use a natural and personal communication style like their human conversation partner.",
keywords = "Chatbots, Customer service, Strategie, Tone of voice, corporate communicatie, klantcontact",
author = "C. Liebrecht and {van Hooijdonk}, Charlotte",
year = "2019",
month = "11",
day = "20",
language = "English",
note = "Conversations 2019 : 3rd international workshop on chatbot research ; Conference date: 19-11-2019 Through 20-11-2019",
url = "https://conversations2019.wordpress.com/",

}

Liebrecht, C & van Hooijdonk, C 2019, 'Creating Humanlike Chatbots: What Chatbot Developers Could Learn From Webcare Employees In Adopting A Conversational Human Voice', Paper presented at Conversations 2019, Amsterdam, Netherlands, 19/11/19 - 20/11/19.

Creating Humanlike Chatbots : What Chatbot Developers Could Learn From Webcare Employees In Adopting A Conversational Human Voice. / Liebrecht, C.; van Hooijdonk, Charlotte.

2019. Paper presented at Conversations 2019, Amsterdam, Netherlands.

Research output: Contribution to conferencePaperScientificpeer-review

TY - CONF

T1 - Creating Humanlike Chatbots

T2 - What Chatbot Developers Could Learn From Webcare Employees In Adopting A Conversational Human Voice

AU - Liebrecht, C.

AU - van Hooijdonk, Charlotte

PY - 2019/11/20

Y1 - 2019/11/20

N2 - Currently, conversations with chatbots are perceived as unnatural andimpersonal. One way to enhance the feeling of humanlike responses is by implementing an engaging communication style (i.e., Conversational Human Voice (CHV); Kelleher, 2009) which positively affects people’s perceptions of the organization. This communication style contributes to the effectiveness of onlinecommunication between organizations and customers (i.e., webcare). This communication style is of high relevance to chatbot design and development. This project aimed to investigate how insights on the use of CHV in organizations’ messages and the perceptions of CHV can be implemented in customer service automation. A corpus study was conducted to investigate which linguistic elements are used in organizations’ messages. Subsequently, an experiment was conducted to assess to what extent linguistic elements contribute to the perception of CHV. Based on these two studies, we investigated whether the amount of CHV can be identified automatically. These findings could be used to design humanlike chatbots that use a natural and personal communication style like their human conversation partner.

AB - Currently, conversations with chatbots are perceived as unnatural andimpersonal. One way to enhance the feeling of humanlike responses is by implementing an engaging communication style (i.e., Conversational Human Voice (CHV); Kelleher, 2009) which positively affects people’s perceptions of the organization. This communication style contributes to the effectiveness of onlinecommunication between organizations and customers (i.e., webcare). This communication style is of high relevance to chatbot design and development. This project aimed to investigate how insights on the use of CHV in organizations’ messages and the perceptions of CHV can be implemented in customer service automation. A corpus study was conducted to investigate which linguistic elements are used in organizations’ messages. Subsequently, an experiment was conducted to assess to what extent linguistic elements contribute to the perception of CHV. Based on these two studies, we investigated whether the amount of CHV can be identified automatically. These findings could be used to design humanlike chatbots that use a natural and personal communication style like their human conversation partner.

KW - Chatbots

KW - Customer service

KW - Strategie

KW - Tone of voice

KW - corporate communicatie

KW - klantcontact

M3 - Paper

ER -