Generative AI Chatbot Prompting for Excellent Customer Service in Tourism

Kekäläinen, Tommi; Heinonen-Kemppi, Johanna; Pesonen, Juho; Sthapit, Erose; Garrod, Brian

doi:10.1080/15332969.2025.2610137

Journal article 198 views 19 downloads

Generative AI Chatbot Prompting for Excellent Customer Service in Tourism

Tommi Kekäläinen, Johanna Heinonen-Kemppi, Juho Pesonen

, Erose Sthapit

, Brian Garrod

Services Marketing Quarterly, Pages: 1 - 23

Swansea University Author: Brian Garrod

PDF | Version of Record

© 2026 The Author(s). This is an Open Access article distributed under the terms of the Creative Commons Attribution-NonCommercial-NoDerivatives License.
Download (2.11MB)

Check full text

DOI (Published version): 10.1080/15332969.2025.2610137

Abstract

The introduction of digital technologies has transformed how businesses achieve and maintain their competitiveness. One of the best-known and most controversial of such technologies is artificial intelligence (AI), which has found many applications across the business domain. AI chatbots are now wid...

Full description

Published in:	Services Marketing Quarterly
ISSN:	1533-2969 1533-2977
Published:	Informa UK Limited 2026
Online Access:	Check full text
URI:	https://cronfa.swan.ac.uk/Record/cronfa70629

first_indexed	2025-10-10T10:23:39Z
last_indexed	2026-02-20T04:20:59Z
id	cronfa70629
recordtype	SURis
fullrecord	<?xml version="1.0"?><rfc1807><datestamp>2026-02-18T12:34:44.3356649</datestamp><bib-version>v2</bib-version><id>70629</id><entry>2025-10-10</entry><title>Generative AI Chatbot Prompting for Excellent Customer Service in Tourism</title><swanseaauthors><author><sid>4f81981d78ed3082b232463da24d1bb9</sid><ORCID>0000-0002-5468-6816</ORCID><firstname>Brian</firstname><surname>Garrod</surname><name>Brian Garrod</name><active>true</active><ethesisStudent>false</ethesisStudent></author></swanseaauthors><date>2025-10-10</date><deptcode>CBAE</deptcode><abstract>The introduction of digital technologies has transformed how businesses achieve and maintain their competitiveness. One of the best-known and most controversial of such technologies is artificial intelligence (AI), which has found many applications across the business domain. AI chatbots are now widely employed to provide such services (Hsu & Lin, Citation2023). Studies have shown that AI chatbots can offer many benefits, including the ability to converse naturally and provide personalized recommendations (Dogru et al., Citation2025). This means that AI chatbots are capable of delivering high levels of service quality, which can positively affect purchase intentions, customer satisfaction, and brand engagement (Blumel et al., Citation2024).Chatbots, however, have been found to have a high failure rate, meaning they do not properly understand the customer’s request and fail to provide an optimal response. The ability of Chatbots to accurately read customers’ emotions and respond accordingly is also vital in customer service contexts (Huang & Rust, Citation2024). When chatbots fail, this can lead to reduced customer trust and negative word of mouth, which can be reflected in falling sales and fewer repeat purchases (Janssen et al., Citation2021). The reasons why chatbots fail are not, however, fully understood; nor, therefore, are the best ways to prevent chatbot failure. There is hence a pressing need to evaluate the customer experience of AI and to develop evidence-based remedies (Hsu & Lin, Citation2023).Especially novel generative-AI chatbots have the potential to change customer-firm interactions. However, the shift from in-person interactions to automation can be challenging for tourism services (Dwivedi et al., Citation2024), with a high failure rate a potential barrier. A possible remedy to the tendency for generative-AI chatbots to fail is to fine-tune them using a technique known as prompting. This involves training the chatbot with further background information and example inquiries to optimize its outputs (Henrickson & Meroño-Peñuela, Citation2025). Robust and reliable studies are, however, needed to explore how prompting might serve to improve the quality of service provided by chatbots and, thereby, the customer experience. AI raises novel issues, such as promises of cost savings and increased work efficiency but also concerns about how AI can handle complex interactions in a culturally appropriate way (Wang, Citation2025).The purpose of this study is, therefore, to investigate the impact of different prompting techniques on the quality of chatbot responses across various dimensions of customer service in the tourism context. In doing so, the study aims to understand how chatbots can enhance customer service and overall customer satisfaction for tourism businesses. As explained in the following section of the article, the focus will be on how to employ prompting best to enhance the effectiveness of customer-service chatbots used by tourism companies and destinations. Tourism is chosen as the context for this study because it relies heavily on service delivery, which necessitates continuous evaluation and improvement of service quality (Augustyn & Ho, Citation1998). Tourism is also a particularly complex service-product, where there are ample opportunities for quality gaps to open and for customer service to be required to remedy them (Augustyn, Citation1998). Finally, tourism is chosen as the context for this study because tourism companies have widely adopted chatbots, which have numerous potential applications in this context (Carvalho & Ivanov, Citation2024).</abstract><type>Journal Article</type><journal>Services Marketing Quarterly</journal><volume>0</volume><journalNumber/><paginationStart>1</paginationStart><paginationEnd>23</paginationEnd><publisher>Informa UK Limited</publisher><placeOfPublication/><isbnPrint/><isbnElectronic/><issnPrint>1533-2969</issnPrint><issnElectronic>1533-2977</issnElectronic><keywords>Artificial intelligence; chatbots; customer service; prompt engineering; service quality</keywords><publishedDay>14</publishedDay><publishedMonth>1</publishedMonth><publishedYear>2026</publishedYear><publishedDate>2026-01-14</publishedDate><doi>10.1080/15332969.2025.2610137</doi><url/><notes/><college>COLLEGE NANME</college><department>Management School</department><CollegeCode>COLLEGE CODE</CollegeCode><DepartmentCode>CBAE</DepartmentCode><institution>Swansea University</institution><apcterm>Another institution paid the OA fee</apcterm><funders/><projectreference/><lastEdited>2026-02-18T12:34:44.3356649</lastEdited><Created>2025-10-10T11:19:58.7277729</Created><path><level id="1">Faculty of Humanities and Social Sciences</level><level id="2">School of Management - Business Management</level></path><authors><author><firstname>Tommi</firstname><surname>Kekäläinen</surname><order>1</order></author><author><firstname>Johanna</firstname><surname>Heinonen-Kemppi</surname><order>2</order></author><author><firstname>Juho</firstname><surname>Pesonen</surname><orcid>0000-0003-0167-9142</orcid><order>3</order></author><author><firstname>Erose</firstname><surname>Sthapit</surname><orcid>0000-0002-1650-3900</orcid><order>4</order></author><author><firstname>Brian</firstname><surname>Garrod</surname><orcid>0000-0002-5468-6816</orcid><order>5</order></author></authors><documents><document><filename>70629__36261__b8a227d39ce74946979c911f98513192.pdf</filename><originalFilename>70629.VoR.pdf</originalFilename><uploaded>2026-02-18T12:24:47.1582515</uploaded><type>Output</type><contentLength>2217433</contentLength><contentType>application/pdf</contentType><version>Version of Record</version><cronfaStatus>true</cronfaStatus><documentNotes>© 2026 The Author(s). This is an Open Access article distributed under the terms of the Creative Commons Attribution-NonCommercial-NoDerivatives License.</documentNotes><copyrightCorrect>true</copyrightCorrect><language>eng</language><licence>http://creativecommons.org/licenses/by-nc-nd/4.0/</licence></document></documents><OutputDurs/></rfc1807>
spelling	2026-02-18T12:34:44.3356649 v2 70629 2025-10-10 Generative AI Chatbot Prompting for Excellent Customer Service in Tourism 4f81981d78ed3082b232463da24d1bb9 0000-0002-5468-6816 Brian Garrod Brian Garrod true false 2025-10-10 CBAE The introduction of digital technologies has transformed how businesses achieve and maintain their competitiveness. One of the best-known and most controversial of such technologies is artificial intelligence (AI), which has found many applications across the business domain. AI chatbots are now widely employed to provide such services (Hsu & Lin, Citation2023). Studies have shown that AI chatbots can offer many benefits, including the ability to converse naturally and provide personalized recommendations (Dogru et al., Citation2025). This means that AI chatbots are capable of delivering high levels of service quality, which can positively affect purchase intentions, customer satisfaction, and brand engagement (Blumel et al., Citation2024).Chatbots, however, have been found to have a high failure rate, meaning they do not properly understand the customer’s request and fail to provide an optimal response. The ability of Chatbots to accurately read customers’ emotions and respond accordingly is also vital in customer service contexts (Huang & Rust, Citation2024). When chatbots fail, this can lead to reduced customer trust and negative word of mouth, which can be reflected in falling sales and fewer repeat purchases (Janssen et al., Citation2021). The reasons why chatbots fail are not, however, fully understood; nor, therefore, are the best ways to prevent chatbot failure. There is hence a pressing need to evaluate the customer experience of AI and to develop evidence-based remedies (Hsu & Lin, Citation2023).Especially novel generative-AI chatbots have the potential to change customer-firm interactions. However, the shift from in-person interactions to automation can be challenging for tourism services (Dwivedi et al., Citation2024), with a high failure rate a potential barrier. A possible remedy to the tendency for generative-AI chatbots to fail is to fine-tune them using a technique known as prompting. This involves training the chatbot with further background information and example inquiries to optimize its outputs (Henrickson & Meroño-Peñuela, Citation2025). Robust and reliable studies are, however, needed to explore how prompting might serve to improve the quality of service provided by chatbots and, thereby, the customer experience. AI raises novel issues, such as promises of cost savings and increased work efficiency but also concerns about how AI can handle complex interactions in a culturally appropriate way (Wang, Citation2025).The purpose of this study is, therefore, to investigate the impact of different prompting techniques on the quality of chatbot responses across various dimensions of customer service in the tourism context. In doing so, the study aims to understand how chatbots can enhance customer service and overall customer satisfaction for tourism businesses. As explained in the following section of the article, the focus will be on how to employ prompting best to enhance the effectiveness of customer-service chatbots used by tourism companies and destinations. Tourism is chosen as the context for this study because it relies heavily on service delivery, which necessitates continuous evaluation and improvement of service quality (Augustyn & Ho, Citation1998). Tourism is also a particularly complex service-product, where there are ample opportunities for quality gaps to open and for customer service to be required to remedy them (Augustyn, Citation1998). Finally, tourism is chosen as the context for this study because tourism companies have widely adopted chatbots, which have numerous potential applications in this context (Carvalho & Ivanov, Citation2024). Journal Article Services Marketing Quarterly 0 1 23 Informa UK Limited 1533-2969 1533-2977 Artificial intelligence; chatbots; customer service; prompt engineering; service quality 14 1 2026 2026-01-14 10.1080/15332969.2025.2610137 COLLEGE NANME Management School COLLEGE CODE CBAE Swansea University Another institution paid the OA fee 2026-02-18T12:34:44.3356649 2025-10-10T11:19:58.7277729 Faculty of Humanities and Social Sciences School of Management - Business Management Tommi Kekäläinen 1 Johanna Heinonen-Kemppi 2 Juho Pesonen 0000-0003-0167-9142 3 Erose Sthapit 0000-0002-1650-3900 4 Brian Garrod 0000-0002-5468-6816 5 70629__36261__b8a227d39ce74946979c911f98513192.pdf 70629.VoR.pdf 2026-02-18T12:24:47.1582515 Output 2217433 application/pdf Version of Record true © 2026 The Author(s). This is an Open Access article distributed under the terms of the Creative Commons Attribution-NonCommercial-NoDerivatives License. true eng http://creativecommons.org/licenses/by-nc-nd/4.0/
title	Generative AI Chatbot Prompting for Excellent Customer Service in Tourism
spellingShingle	Generative AI Chatbot Prompting for Excellent Customer Service in Tourism Brian Garrod
title_short	Generative AI Chatbot Prompting for Excellent Customer Service in Tourism
title_full	Generative AI Chatbot Prompting for Excellent Customer Service in Tourism
title_fullStr	Generative AI Chatbot Prompting for Excellent Customer Service in Tourism
title_full_unstemmed	Generative AI Chatbot Prompting for Excellent Customer Service in Tourism
title_sort	Generative AI Chatbot Prompting for Excellent Customer Service in Tourism
author_id_str_mv	4f81981d78ed3082b232463da24d1bb9
author_id_fullname_str_mv	4f81981d78ed3082b232463da24d1bb9_***_Brian Garrod
author	Brian Garrod
author2	Tommi Kekäläinen Johanna Heinonen-Kemppi Juho Pesonen Erose Sthapit Brian Garrod
format	Journal article
container_title	Services Marketing Quarterly
container_volume	0
container_start_page	1
publishDate	2026
institution	Swansea University
issn	1533-2969 1533-2977
doi_str_mv	10.1080/15332969.2025.2610137
publisher	Informa UK Limited
college_str	Faculty of Humanities and Social Sciences
hierarchytype
hierarchy_top_id	facultyofhumanitiesandsocialsciences
hierarchy_top_title	Faculty of Humanities and Social Sciences
hierarchy_parent_id	facultyofhumanitiesandsocialsciences
hierarchy_parent_title	Faculty of Humanities and Social Sciences
department_str	School of Management - Business Management{{{_:::_}}}Faculty of Humanities and Social Sciences{{{_:::_}}}School of Management - Business Management
document_store_str	1
active_str	0
description	The introduction of digital technologies has transformed how businesses achieve and maintain their competitiveness. One of the best-known and most controversial of such technologies is artificial intelligence (AI), which has found many applications across the business domain. AI chatbots are now widely employed to provide such services (Hsu & Lin, Citation2023). Studies have shown that AI chatbots can offer many benefits, including the ability to converse naturally and provide personalized recommendations (Dogru et al., Citation2025). This means that AI chatbots are capable of delivering high levels of service quality, which can positively affect purchase intentions, customer satisfaction, and brand engagement (Blumel et al., Citation2024).Chatbots, however, have been found to have a high failure rate, meaning they do not properly understand the customer’s request and fail to provide an optimal response. The ability of Chatbots to accurately read customers’ emotions and respond accordingly is also vital in customer service contexts (Huang & Rust, Citation2024). When chatbots fail, this can lead to reduced customer trust and negative word of mouth, which can be reflected in falling sales and fewer repeat purchases (Janssen et al., Citation2021). The reasons why chatbots fail are not, however, fully understood; nor, therefore, are the best ways to prevent chatbot failure. There is hence a pressing need to evaluate the customer experience of AI and to develop evidence-based remedies (Hsu & Lin, Citation2023).Especially novel generative-AI chatbots have the potential to change customer-firm interactions. However, the shift from in-person interactions to automation can be challenging for tourism services (Dwivedi et al., Citation2024), with a high failure rate a potential barrier. A possible remedy to the tendency for generative-AI chatbots to fail is to fine-tune them using a technique known as prompting. This involves training the chatbot with further background information and example inquiries to optimize its outputs (Henrickson & Meroño-Peñuela, Citation2025). Robust and reliable studies are, however, needed to explore how prompting might serve to improve the quality of service provided by chatbots and, thereby, the customer experience. AI raises novel issues, such as promises of cost savings and increased work efficiency but also concerns about how AI can handle complex interactions in a culturally appropriate way (Wang, Citation2025).The purpose of this study is, therefore, to investigate the impact of different prompting techniques on the quality of chatbot responses across various dimensions of customer service in the tourism context. In doing so, the study aims to understand how chatbots can enhance customer service and overall customer satisfaction for tourism businesses. As explained in the following section of the article, the focus will be on how to employ prompting best to enhance the effectiveness of customer-service chatbots used by tourism companies and destinations. Tourism is chosen as the context for this study because it relies heavily on service delivery, which necessitates continuous evaluation and improvement of service quality (Augustyn & Ho, Citation1998). Tourism is also a particularly complex service-product, where there are ample opportunities for quality gaps to open and for customer service to be required to remedy them (Augustyn, Citation1998). Finally, tourism is chosen as the context for this study because tourism companies have widely adopted chatbots, which have numerous potential applications in this context (Carvalho & Ivanov, Citation2024).
published_date	2026-01-14T05:32:37Z
_version_	1857802319469477888
score	11.096892

Generative AI Chatbot Prompting for Excellent Customer Service in Tourism

Similar Items