Understanding the user experience through interaction types in customer service chatbots
Autor(a) principal: | |
---|---|
Data de Publicação: | 2023 |
Tipo de documento: | Dissertação |
Idioma: | por |
Título da fonte: | Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
Texto Completo: | http://hdl.handle.net/10400.5/30054 |
Resumo: | Understanding the user experience through interaction types in customer service chatbots. Chatbots have become increasingly popular in recent years due to their ability to automate tasks, improve customer engagement, and reduce operational costs for businesses. They are also seen as a way to improve the user experience by providing quick and easy access to information and services through messaging platforms that are already familiar to users. With the raising and appearance of this type of communication, this research aims to offer an insightful analysis of chatbot interaction types, their optimal applications, and their suitability for various tasks. It also seeks to provide guidance on key considerations and pathways for effectively implementing chatbot technology. In order to carry out this research study, we created four prototypes using Chatbot.com. In each scenario, we trained two chatbots: one using AI with text input and the other using rules with button input. Based on these methods, research questions were considered to further investigate the performance, usability, satisfaction and mental perception. To assess chatbot interaction types' performance in specific tasks, we use metrics like Customer satisfaction (CSAT), Net promoter score (NPS), Emotional response (SAM), Usability (SUS), or the Post-Task Workload (NASA-TLX). Overall, we find better results with the rules-based button input approach. We find and identify certain conditions that could lead into these results, such as task complexity or the trained approach. This study demonstrates that rules-based chatbots outperform other types in certain conditions and tasks. It underscores the importance of analyzing task-specific outcomes, mental workload, and complexity perception to ensure user satisfaction and protect brand reputation. Additionally, the underlying technology significantly influences chatbot performance and task completion. |
id |
RCAP_a17e70f8a9cdea27aad6a9a94cd77a3f |
---|---|
oai_identifier_str |
oai:www.repository.utl.pt:10400.5/30054 |
network_acronym_str |
RCAP |
network_name_str |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
repository_id_str |
7160 |
spelling |
Understanding the user experience through interaction types in customer service chatbotsChatbotsVirtual agentsChatbots interactionUser experience chatbotsCustomer service chatbotsConversational chatbotsRules-based chatbotsChatbot performanceChatbot usabilityChatbot tasksAgentes virtuaisInteração de chatbotsExperiência de utilizador com chatbotsChatbots de serviço ao clienteChatbots conversacionaisChatbots baseados em regrasDesempenho de chatbotsUsabilidade de chatbotsTarefas de chatbotsDomínio/Área Científica::Ciências Sociais::Outras Ciências SociaisUnderstanding the user experience through interaction types in customer service chatbots. Chatbots have become increasingly popular in recent years due to their ability to automate tasks, improve customer engagement, and reduce operational costs for businesses. They are also seen as a way to improve the user experience by providing quick and easy access to information and services through messaging platforms that are already familiar to users. With the raising and appearance of this type of communication, this research aims to offer an insightful analysis of chatbot interaction types, their optimal applications, and their suitability for various tasks. It also seeks to provide guidance on key considerations and pathways for effectively implementing chatbot technology. In order to carry out this research study, we created four prototypes using Chatbot.com. In each scenario, we trained two chatbots: one using AI with text input and the other using rules with button input. Based on these methods, research questions were considered to further investigate the performance, usability, satisfaction and mental perception. To assess chatbot interaction types' performance in specific tasks, we use metrics like Customer satisfaction (CSAT), Net promoter score (NPS), Emotional response (SAM), Usability (SUS), or the Post-Task Workload (NASA-TLX). Overall, we find better results with the rules-based button input approach. We find and identify certain conditions that could lead into these results, such as task complexity or the trained approach. This study demonstrates that rules-based chatbots outperform other types in certain conditions and tasks. It underscores the importance of analyzing task-specific outcomes, mental workload, and complexity perception to ensure user satisfaction and protect brand reputation. Additionally, the underlying technology significantly influences chatbot performance and task completion.Compreender a experiência de utilizador através dos tipos de interação em chatbots de serviço ao cliente Chatbots têm se tornado cada vez mais populares nos últimos anos devido à sua capacidade de automatizar tarefas, melhorar o envolvimento do cliente e reduzir os custos operacionais para as empresas. Eles também são vistos como uma maneira de aprimorar a experiência do utilizador, fornecendo acesso rápido e fácil a informações e/ou serviços através de plataformas de mensagens que são já reconhecidos meios de interação. Com o surgimento e a crescente adoção deste tipo de comunicação, este estudo tem como objetivo oferecer uma análise esclarecedora dos tipos de interação de chatbots, quais as suas aplicações e qual a adequação para diversas tarefas. Procura também debruçar-se sobre orientações, demonstrando considerações e caminhos para uma implementação eficaz da tecnologia e respectivamente, chatbots. Para a realização deste estudo, foram criados quatro protótipos usando a platforma Chatbot.com. Em cada cenário, treinamos dois chatbots: um usando AI com inserção manual de texto e o outro usando regras definidas com navegação através de botões. Com base nessas metodologias, foram consideradas questões de pesquisa para investigar o desempenho, a usabilidade, a satisfação e a percepção mental dos utilizadores. Para avaliar o desempenho dos tipos de interação em tarefas específicas, utilizamos métricas como Satisfação do Cliente (CSAT), Recomendação do serviço (NPS), Resposta Emocional (SAM), Usabilidade (SUS) ou Carga de Trabalho Pós-Tarefa (NASA-TLX). No geral, reportam-se melhores resultados numa abordagem usando regras definidas com navegação através de botões. Identificamos também certas condições que podem levar a estes resultados, como a complexidade da tarefa ou a abordagem de treino efetuada no sistema de AI. Este estudo demonstra que os chatbots baseados em regras definidas com navegação através de botões, superam a abordagem de AI com inserção manual de texto. No entanto, também demonstra alguns fatores que são necessários ter em consideração. Assim, destacamos também a importância de analisar a especificidade da tarefa, a carga mental e a percepção de complexidade para garantir a satisfação do utilizador. Além disso, a tecnologia subjacente influencia significativamente o desempenho do chatbot e a conclusão da tarefa.Machado, Paulo Ignácio Noriega PintoCotrim, Teresa Margarida PatroneRepositório da Universidade de LisboaBarata, Pedro Miguel Santiago2024-02-05T16:53:38Z20232023-01-01T00:00:00Zinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/masterThesisapplication/pdfhttp://hdl.handle.net/10400.5/30054TID:203467051porinfo:eu-repo/semantics/openAccessreponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãoinstacron:RCAAP2024-02-11T01:31:32Zoai:www.repository.utl.pt:10400.5/30054Portal AgregadorONGhttps://www.rcaap.pt/oai/openaireopendoar:71602024-03-20T02:37:37.385198Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãofalse |
dc.title.none.fl_str_mv |
Understanding the user experience through interaction types in customer service chatbots |
title |
Understanding the user experience through interaction types in customer service chatbots |
spellingShingle |
Understanding the user experience through interaction types in customer service chatbots Barata, Pedro Miguel Santiago Chatbots Virtual agents Chatbots interaction User experience chatbots Customer service chatbots Conversational chatbots Rules-based chatbots Chatbot performance Chatbot usability Chatbot tasks Agentes virtuais Interação de chatbots Experiência de utilizador com chatbots Chatbots de serviço ao cliente Chatbots conversacionais Chatbots baseados em regras Desempenho de chatbots Usabilidade de chatbots Tarefas de chatbots Domínio/Área Científica::Ciências Sociais::Outras Ciências Sociais |
title_short |
Understanding the user experience through interaction types in customer service chatbots |
title_full |
Understanding the user experience through interaction types in customer service chatbots |
title_fullStr |
Understanding the user experience through interaction types in customer service chatbots |
title_full_unstemmed |
Understanding the user experience through interaction types in customer service chatbots |
title_sort |
Understanding the user experience through interaction types in customer service chatbots |
author |
Barata, Pedro Miguel Santiago |
author_facet |
Barata, Pedro Miguel Santiago |
author_role |
author |
dc.contributor.none.fl_str_mv |
Machado, Paulo Ignácio Noriega Pinto Cotrim, Teresa Margarida Patrone Repositório da Universidade de Lisboa |
dc.contributor.author.fl_str_mv |
Barata, Pedro Miguel Santiago |
dc.subject.por.fl_str_mv |
Chatbots Virtual agents Chatbots interaction User experience chatbots Customer service chatbots Conversational chatbots Rules-based chatbots Chatbot performance Chatbot usability Chatbot tasks Agentes virtuais Interação de chatbots Experiência de utilizador com chatbots Chatbots de serviço ao cliente Chatbots conversacionais Chatbots baseados em regras Desempenho de chatbots Usabilidade de chatbots Tarefas de chatbots Domínio/Área Científica::Ciências Sociais::Outras Ciências Sociais |
topic |
Chatbots Virtual agents Chatbots interaction User experience chatbots Customer service chatbots Conversational chatbots Rules-based chatbots Chatbot performance Chatbot usability Chatbot tasks Agentes virtuais Interação de chatbots Experiência de utilizador com chatbots Chatbots de serviço ao cliente Chatbots conversacionais Chatbots baseados em regras Desempenho de chatbots Usabilidade de chatbots Tarefas de chatbots Domínio/Área Científica::Ciências Sociais::Outras Ciências Sociais |
description |
Understanding the user experience through interaction types in customer service chatbots. Chatbots have become increasingly popular in recent years due to their ability to automate tasks, improve customer engagement, and reduce operational costs for businesses. They are also seen as a way to improve the user experience by providing quick and easy access to information and services through messaging platforms that are already familiar to users. With the raising and appearance of this type of communication, this research aims to offer an insightful analysis of chatbot interaction types, their optimal applications, and their suitability for various tasks. It also seeks to provide guidance on key considerations and pathways for effectively implementing chatbot technology. In order to carry out this research study, we created four prototypes using Chatbot.com. In each scenario, we trained two chatbots: one using AI with text input and the other using rules with button input. Based on these methods, research questions were considered to further investigate the performance, usability, satisfaction and mental perception. To assess chatbot interaction types' performance in specific tasks, we use metrics like Customer satisfaction (CSAT), Net promoter score (NPS), Emotional response (SAM), Usability (SUS), or the Post-Task Workload (NASA-TLX). Overall, we find better results with the rules-based button input approach. We find and identify certain conditions that could lead into these results, such as task complexity or the trained approach. This study demonstrates that rules-based chatbots outperform other types in certain conditions and tasks. It underscores the importance of analyzing task-specific outcomes, mental workload, and complexity perception to ensure user satisfaction and protect brand reputation. Additionally, the underlying technology significantly influences chatbot performance and task completion. |
publishDate |
2023 |
dc.date.none.fl_str_mv |
2023 2023-01-01T00:00:00Z 2024-02-05T16:53:38Z |
dc.type.status.fl_str_mv |
info:eu-repo/semantics/publishedVersion |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/masterThesis |
format |
masterThesis |
status_str |
publishedVersion |
dc.identifier.uri.fl_str_mv |
http://hdl.handle.net/10400.5/30054 TID:203467051 |
url |
http://hdl.handle.net/10400.5/30054 |
identifier_str_mv |
TID:203467051 |
dc.language.iso.fl_str_mv |
por |
language |
por |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.format.none.fl_str_mv |
application/pdf |
dc.source.none.fl_str_mv |
reponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação instacron:RCAAP |
instname_str |
Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação |
instacron_str |
RCAAP |
institution |
RCAAP |
reponame_str |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
collection |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
repository.name.fl_str_mv |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação |
repository.mail.fl_str_mv |
|
_version_ |
1799137426848874496 |