A behaviourally informed chatbot increases vaccination rates in Argentina more than a one-way reminder DOI Creative Commons
Dan Brown, Adelaida Barrera, Lorena Itatí Ibañez

и другие.

Nature Human Behaviour, Год журнала: 2024, Номер unknown

Опубликована: Окт. 18, 2024

Maintaining COVID-19 vaccine demand was key to ending the global health emergency. To help do this, many governments used chatbots that provided personalized information guiding people on where, when and how get vaccinated. We designed tested a WhatsApp chatbot understand whether two-way interactive messaging incorporating behaviourally informed functionalities could perform better than one-way message reminders. ran large-scale preregistered randomized controlled trial with 249,705 participants in Argentina, measuring vaccinations using Ministry of Health records. The more tripled uptake compared control group (a 1.6 percentage point increase (95% confidence interval, (1.36 pp, 1.77 pp)) nearly doubled reminder 1 (0.83 1.17 pp)). Communications tools simplify user journey can vaccination traditional reminders may have applications other behaviours.

Язык: Английский

The ethical aspects of integrating sentiment and emotion analysis in chatbots for depression intervention DOI Creative Commons
Kerstin Denecke, Elia Gabarrón

Frontiers in Psychiatry, Год журнала: 2024, Номер 15

Опубликована: Ноя. 14, 2024

Digital health interventions specifically those realized as chatbots are increasingly available for mental health. They include technologies based on artificial intelligence that assess user's sentiment and emotions the purpose of responding in an empathetic way, or treatment purposes, e.g. analyzing expressed suggesting interventions.

Язык: Английский

Процитировано

2

Are Chatbots the New Relationship Experts? Insights from Three Studies DOI Open Access
Laura M. Vowels

Опубликована: Сен. 23, 2023

Relationship distress is among the most important predictors of individual distress. Over one in three couples report relationships but despite distress, only rarely seek help from couple therapists and instead prefer to information advice online. The recent breakthroughs development humanlike artificial intelligence-powered chatbots such as ChatGPT have recently made it possible develop which respond therapeutically. Early research suggests that they outperform physicians helpfulness empathy answering health-related questions. However, we do not yet know how well questions about relationships. Across studies, evaluated performance responding relationship-related engaging a single session relationship therapy. In Studies 1 2, demonstrated are perceived more helpful empathic than experts Study 3, showed rate sessions with chatbot high on attributes empathy, active listening, exploration. Limitations include repetitive inadequate assessment risk. findings show potential using support highlight limitations need be addressed before can safely adopted for interventions.

Язык: Английский

Процитировано

4

Combining statistical dialog management and intent recognition for enhanced response selection DOI Creative Commons
David Griol, Zoraida Callejas

Logic Journal of IGPL, Год журнала: 2024, Номер unknown

Опубликована: Май 9, 2024

Abstract Conversational interfaces are becoming ubiquitous in an increasing number of application domains as Artificial Intelligence, Natural Language Processing and Machine Learning methods associated with the recognition, understanding generation natural language advance by leaps bounds. However, designing dialog model these systems is still a very demanding task requiring great deal effort given information sources to be considered related analysis user utterances, interaction context, repositories, etc. In this paper, we present general framework for quality system responses combining statistical management technique deep learning-based intention recognizer that allow replacing initially selected other presumably better candidates. This approach portable different task-oriented domains, diversity methodologies estimation techniques. We have evaluated our two-step proposal using two conversational systems, assessed several recognition used developed modules dynamically select responses. The results evaluation show proposed achieves satisfactory making it possible reduce non-coherent them more coherent alternatives.

Язык: Английский

Процитировано

1

Innovative Approaches to Addressing Pediatric Mental Health DOI
Gary Maslow, Richard J. Chung,

Nicole Heilbron

и другие.

Pediatric Clinics of North America, Год журнала: 2024, Номер 71(6), С. 1151 - 1164

Опубликована: Авг. 30, 2024

Язык: Английский

Процитировано

1

A behaviourally informed chatbot increases vaccination rates in Argentina more than a one-way reminder DOI Creative Commons
Dan Brown, Adelaida Barrera, Lorena Itatí Ibañez

и другие.

Nature Human Behaviour, Год журнала: 2024, Номер unknown

Опубликована: Окт. 18, 2024

Maintaining COVID-19 vaccine demand was key to ending the global health emergency. To help do this, many governments used chatbots that provided personalized information guiding people on where, when and how get vaccinated. We designed tested a WhatsApp chatbot understand whether two-way interactive messaging incorporating behaviourally informed functionalities could perform better than one-way message reminders. ran large-scale preregistered randomized controlled trial with 249,705 participants in Argentina, measuring vaccinations using Ministry of Health records. The more tripled uptake compared control group (a 1.6 percentage point increase (95% confidence interval, (1.36 pp, 1.77 pp)) nearly doubled reminder 1 (0.83 1.17 pp)). Communications tools simplify user journey can vaccination traditional reminders may have applications other behaviours.

Язык: Английский

Процитировано

1