Evaluating User Experience With a Chatbot Designed as a Public Health Response to the COVID-19 Pandemic in Brazil: Mixed Methods Study
BackgroundThe potential of chatbots for screening and monitoring COVID-19 was envisioned since the outbreak of the disease. Chatbots can help disseminate up-to-date and trustworthy information, promote healthy social behavior, and support the provision of health care services...
| Main Authors: | , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
JMIR Publications
2023-04-01
|
| Series: | JMIR Human Factors |
| Online Access: | https://humanfactors.jmir.org/2023/1/e43135 |
| _version_ | 1797734233178898432 |
|---|---|
| author | Bruno Azevedo Chagas Adriana Silvina Pagano Raquel Oliveira Prates Elisa Cordeiro Praes Kícila Ferreguetti Helena Vaz Zilma Silveira Nogueira Reis Leonardo Bonisson Ribeiro Antonio Luiz Pinho Ribeiro Thais Marques Pedroso Alline Beleigoli Clara Rodrigues Alves Oliveira Milena Soriano Marcolino |
| author_facet | Bruno Azevedo Chagas Adriana Silvina Pagano Raquel Oliveira Prates Elisa Cordeiro Praes Kícila Ferreguetti Helena Vaz Zilma Silveira Nogueira Reis Leonardo Bonisson Ribeiro Antonio Luiz Pinho Ribeiro Thais Marques Pedroso Alline Beleigoli Clara Rodrigues Alves Oliveira Milena Soriano Marcolino |
| author_sort | Bruno Azevedo Chagas |
| collection | DOAJ |
| description |
BackgroundThe potential of chatbots for screening and monitoring COVID-19 was envisioned since the outbreak of the disease. Chatbots can help disseminate up-to-date and trustworthy information, promote healthy social behavior, and support the provision of health care services safely and at scale. In this scenario and in view of its far-reaching postpandemic impact, it is important to evaluate user experience with this kind of application.
ObjectiveWe aimed to evaluate the quality of user experience with a COVID-19 chatbot designed by a large telehealth service in Brazil, focusing on the usability of real users and the exploration of strengths and shortcomings of the chatbot, as revealed in reports by participants in simulated scenarios.
MethodsWe examined a chatbot developed by a multidisciplinary team and used it as a component within the workflow of a local public health care service. The chatbot had 2 core functionalities: assisting web-based screening of COVID-19 symptom severity and providing evidence-based information to the population. From October 2020 to January 2021, we conducted a mixed methods approach and performed a 2-fold evaluation of user experience with our chatbot by following 2 methods: a posttask usability Likert-scale survey presented to all users after concluding their interaction with the bot and an interview with volunteer participants who engaged in a simulated interaction with the bot guided by the interviewer.
ResultsUsability assessment with 63 users revealed very good scores for chatbot usefulness (4.57), likelihood of being recommended (4.48), ease of use (4.44), and user satisfaction (4.38). Interviews with 15 volunteers provided insights into the strengths and shortcomings of our bot. Comments on the positive aspects and problems reported by users were analyzed in terms of recurrent themes. We identified 6 positive aspects and 15 issues organized in 2 categories: usability of the chatbot and health support offered by it, the former referring to usability of the chatbot and how users can interact with it and the latter referring to the chatbot’s goal in supporting people during the pandemic through the screening process and education to users through informative content. We found 6 themes accounting for what people liked most about our chatbot and why they found it useful—3 themes pertaining to the usability domain and 3 themes regarding health support. Our findings also identified 15 types of problems producing a negative impact on users—10 of them related to the usability of the chatbot and 5 related to the health support it provides.
ConclusionsOur results indicate that users had an overall positive experience with the chatbot and found the health support relevant. Nonetheless, qualitative evaluation of the chatbot indicated challenges and directions to be pursued in improving not only our COVID-19 chatbot but also health chatbots in general. |
| first_indexed | 2024-03-12T12:41:20Z |
| format | Article |
| id | doaj.art-5c806fb0041743b38e4602e4caa0ad99 |
| institution | Directory Open Access Journal |
| issn | 2292-9495 |
| language | English |
| last_indexed | 2024-03-12T12:41:20Z |
| publishDate | 2023-04-01 |
| publisher | JMIR Publications |
| record_format | Article |
| series | JMIR Human Factors |
| spelling | doaj.art-5c806fb0041743b38e4602e4caa0ad992023-08-28T23:50:08ZengJMIR PublicationsJMIR Human Factors2292-94952023-04-0110e4313510.2196/43135Evaluating User Experience With a Chatbot Designed as a Public Health Response to the COVID-19 Pandemic in Brazil: Mixed Methods StudyBruno Azevedo Chagashttps://orcid.org/0000-0002-8571-3135Adriana Silvina Paganohttps://orcid.org/0000-0002-3150-3503Raquel Oliveira Prateshttps://orcid.org/0000-0002-7128-4974Elisa Cordeiro Praeshttps://orcid.org/0000-0001-6495-993XKícila Ferreguettihttps://orcid.org/0000-0002-1919-0073Helena Vazhttps://orcid.org/0000-0001-9754-1425Zilma Silveira Nogueira Reishttps://orcid.org/0000-0001-6374-9295Leonardo Bonisson Ribeirohttps://orcid.org/0000-0001-9035-0722Antonio Luiz Pinho Ribeirohttps://orcid.org/0000-0002-2740-0042Thais Marques Pedrosohttps://orcid.org/0000-0003-0149-9731Alline Beleigolihttps://orcid.org/0000-0002-7848-3183Clara Rodrigues Alves Oliveirahttps://orcid.org/0000-0002-9437-2344Milena Soriano Marcolinohttps://orcid.org/0000-0003-4278-3771 BackgroundThe potential of chatbots for screening and monitoring COVID-19 was envisioned since the outbreak of the disease. Chatbots can help disseminate up-to-date and trustworthy information, promote healthy social behavior, and support the provision of health care services safely and at scale. In this scenario and in view of its far-reaching postpandemic impact, it is important to evaluate user experience with this kind of application. ObjectiveWe aimed to evaluate the quality of user experience with a COVID-19 chatbot designed by a large telehealth service in Brazil, focusing on the usability of real users and the exploration of strengths and shortcomings of the chatbot, as revealed in reports by participants in simulated scenarios. MethodsWe examined a chatbot developed by a multidisciplinary team and used it as a component within the workflow of a local public health care service. The chatbot had 2 core functionalities: assisting web-based screening of COVID-19 symptom severity and providing evidence-based information to the population. From October 2020 to January 2021, we conducted a mixed methods approach and performed a 2-fold evaluation of user experience with our chatbot by following 2 methods: a posttask usability Likert-scale survey presented to all users after concluding their interaction with the bot and an interview with volunteer participants who engaged in a simulated interaction with the bot guided by the interviewer. ResultsUsability assessment with 63 users revealed very good scores for chatbot usefulness (4.57), likelihood of being recommended (4.48), ease of use (4.44), and user satisfaction (4.38). Interviews with 15 volunteers provided insights into the strengths and shortcomings of our bot. Comments on the positive aspects and problems reported by users were analyzed in terms of recurrent themes. We identified 6 positive aspects and 15 issues organized in 2 categories: usability of the chatbot and health support offered by it, the former referring to usability of the chatbot and how users can interact with it and the latter referring to the chatbot’s goal in supporting people during the pandemic through the screening process and education to users through informative content. We found 6 themes accounting for what people liked most about our chatbot and why they found it useful—3 themes pertaining to the usability domain and 3 themes regarding health support. Our findings also identified 15 types of problems producing a negative impact on users—10 of them related to the usability of the chatbot and 5 related to the health support it provides. ConclusionsOur results indicate that users had an overall positive experience with the chatbot and found the health support relevant. Nonetheless, qualitative evaluation of the chatbot indicated challenges and directions to be pursued in improving not only our COVID-19 chatbot but also health chatbots in general.https://humanfactors.jmir.org/2023/1/e43135 |
| spellingShingle | Bruno Azevedo Chagas Adriana Silvina Pagano Raquel Oliveira Prates Elisa Cordeiro Praes Kícila Ferreguetti Helena Vaz Zilma Silveira Nogueira Reis Leonardo Bonisson Ribeiro Antonio Luiz Pinho Ribeiro Thais Marques Pedroso Alline Beleigoli Clara Rodrigues Alves Oliveira Milena Soriano Marcolino Evaluating User Experience With a Chatbot Designed as a Public Health Response to the COVID-19 Pandemic in Brazil: Mixed Methods Study JMIR Human Factors |
| title | Evaluating User Experience With a Chatbot Designed as a Public Health Response to the COVID-19 Pandemic in Brazil: Mixed Methods Study |
| title_full | Evaluating User Experience With a Chatbot Designed as a Public Health Response to the COVID-19 Pandemic in Brazil: Mixed Methods Study |
| title_fullStr | Evaluating User Experience With a Chatbot Designed as a Public Health Response to the COVID-19 Pandemic in Brazil: Mixed Methods Study |
| title_full_unstemmed | Evaluating User Experience With a Chatbot Designed as a Public Health Response to the COVID-19 Pandemic in Brazil: Mixed Methods Study |
| title_short | Evaluating User Experience With a Chatbot Designed as a Public Health Response to the COVID-19 Pandemic in Brazil: Mixed Methods Study |
| title_sort | evaluating user experience with a chatbot designed as a public health response to the covid 19 pandemic in brazil mixed methods study |
| url | https://humanfactors.jmir.org/2023/1/e43135 |
| work_keys_str_mv | AT brunoazevedochagas evaluatinguserexperiencewithachatbotdesignedasapublichealthresponsetothecovid19pandemicinbrazilmixedmethodsstudy AT adrianasilvinapagano evaluatinguserexperiencewithachatbotdesignedasapublichealthresponsetothecovid19pandemicinbrazilmixedmethodsstudy AT raqueloliveiraprates evaluatinguserexperiencewithachatbotdesignedasapublichealthresponsetothecovid19pandemicinbrazilmixedmethodsstudy AT elisacordeiropraes evaluatinguserexperiencewithachatbotdesignedasapublichealthresponsetothecovid19pandemicinbrazilmixedmethodsstudy AT kicilaferreguetti evaluatinguserexperiencewithachatbotdesignedasapublichealthresponsetothecovid19pandemicinbrazilmixedmethodsstudy AT helenavaz evaluatinguserexperiencewithachatbotdesignedasapublichealthresponsetothecovid19pandemicinbrazilmixedmethodsstudy AT zilmasilveiranogueirareis evaluatinguserexperiencewithachatbotdesignedasapublichealthresponsetothecovid19pandemicinbrazilmixedmethodsstudy AT leonardobonissonribeiro evaluatinguserexperiencewithachatbotdesignedasapublichealthresponsetothecovid19pandemicinbrazilmixedmethodsstudy AT antonioluizpinhoribeiro evaluatinguserexperiencewithachatbotdesignedasapublichealthresponsetothecovid19pandemicinbrazilmixedmethodsstudy AT thaismarquespedroso evaluatinguserexperiencewithachatbotdesignedasapublichealthresponsetothecovid19pandemicinbrazilmixedmethodsstudy AT allinebeleigoli evaluatinguserexperiencewithachatbotdesignedasapublichealthresponsetothecovid19pandemicinbrazilmixedmethodsstudy AT clararodriguesalvesoliveira evaluatinguserexperiencewithachatbotdesignedasapublichealthresponsetothecovid19pandemicinbrazilmixedmethodsstudy AT milenasorianomarcolino evaluatinguserexperiencewithachatbotdesignedasapublichealthresponsetothecovid19pandemicinbrazilmixedmethodsstudy |