AI Chatbots for Well-Being Adoption Drivers: A Machine Learning Approach

Jorge Tavares; Yanrong Yang; Tiago Oliveira

doi:10.1016/j.procs.2026.03.112

AI Chatbots for Well-Being Adoption Drivers: A Machine Learning Approach

Jorge Tavares, Yanrong Yang, Tiago Oliveira

Research output: Contribution to journal › Conference article › peer-review

7 Downloads (Pure)

Abstract

The global mental health sector lacks resources particularly in low- and middle-income countries. AI- chatbots are increasingly recognized as a promising resource to support mental health. However, the acceptance of AI chatbots in the field of mental health is still low. Our study aims to predict their usage, identifying the features which are more relevant for the prediction. An online survey was created in China with 400 valid responses collected. For our prediction exercise we used three Machine Learning algorithms: decision tree, logistic regression, and random forest. The accuracy of these algorithms ranged from 64-71%. Age was the most important feature to explain usage. Younger people value the compatibility of AI chatbots for well-being with their lifestyle, and older people are influenced by social factors to use them. Higher complexity can be an obstacle for AI chatbots for well-being use.

Original language	English
Pages (from-to)	1291-1298
Number of pages	8
Journal	Procedia Computer Science
Volume	278
Early online date	24 Mar 2026
DOIs	https://doi.org/10.1016/j.procs.2026.03.112
Publication status	Published - 2026
Event	CENTERIS – International Conference on ENTERprise Information Systems / ProjMAN – International Conference on Project MANagement / HCist – International Conference on Health and Social Care Information Systems and Technologies 2025 - Khalidiya Palace Rayhaan by Rotana, Abu Dhabi, United Arab Emirates Duration: 26 Nov 2025 → 28 Nov 2025 Conference number: 17 https://centeris.scika.org/

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 3 Good Health and Well-being

Keywords

Artificial Intelligence
Mental Health
AI chatbots
Machine Learning
Technology Adoption

Access to Document

10.1016/j.procs.2026.03.112Licence: CC BY-NC-ND

AI_Chatbots_for_Well-Being_Adoption_DriversFinal published version, 805 KBLicence: CC BY-NC-ND

Cite this

@article{20928843d9af45798a89e22778608312,

title = "AI Chatbots for Well-Being Adoption Drivers: A Machine Learning Approach",

abstract = "The global mental health sector lacks resources particularly in low- and middle-income countries. AI- chatbots are increasingly recognized as a promising resource to support mental health. However, the acceptance of AI chatbots in the field of mental health is still low. Our study aims to predict their usage, identifying the features which are more relevant for the prediction. An online survey was created in China with 400 valid responses collected. For our prediction exercise we used three Machine Learning algorithms: decision tree, logistic regression, and random forest. The accuracy of these algorithms ranged from 64-71\%. Age was the most important feature to explain usage. Younger people value the compatibility of AI chatbots for well-being with their lifestyle, and older people are influenced by social factors to use them. Higher complexity can be an obstacle for AI chatbots for well-being use.",

keywords = "Artificial Intelligence, Mental Health, AI chatbots, Machine Learning, Technology Adoption",

author = "Jorge Tavares and Yanrong Yang and Tiago Oliveira",

note = "https://doi.org/10.54499/UID/04152/2025\# https://doi.org/10.54499/UID/PRR/04152/2025\# Tavares, J., Yang, Y., \& Oliveira, T. (2026). AI Chatbots for Well-Being Adoption Drivers: A Machine Learning Approach. Procedia Computer Science, 278, 1291-1298. https://doi.org/10.1016/j.procs.2026.03.112; CENTERIS – International Conference on ENTERprise Information Systems / ProjMAN – International Conference on Project MANagement / HCist – International Conference on Health and Social Care Information Systems and Technologies 2025, CENTERIS/ProjMAN/HCist 2025 ; Conference date: 26-11-2025 Through 28-11-2025",

year = "2026",

doi = "10.1016/j.procs.2026.03.112",

language = "English",

volume = "278",

pages = "1291--1298",

journal = "Procedia Computer Science",

issn = "1877-0509",

publisher = "Elsevier",

url = "https://centeris.scika.org/",

}

TY - JOUR

T1 - AI Chatbots for Well-Being Adoption Drivers

T2 - CENTERIS – International Conference on ENTERprise Information Systems / ProjMAN – International Conference on Project MANagement / HCist – International Conference on Health and Social Care Information Systems and Technologies 2025

AU - Tavares, Jorge

AU - Yang, Yanrong

AU - Oliveira, Tiago

N1 - Conference code: 17

PY - 2026

Y1 - 2026

N2 - The global mental health sector lacks resources particularly in low- and middle-income countries. AI- chatbots are increasingly recognized as a promising resource to support mental health. However, the acceptance of AI chatbots in the field of mental health is still low. Our study aims to predict their usage, identifying the features which are more relevant for the prediction. An online survey was created in China with 400 valid responses collected. For our prediction exercise we used three Machine Learning algorithms: decision tree, logistic regression, and random forest. The accuracy of these algorithms ranged from 64-71%. Age was the most important feature to explain usage. Younger people value the compatibility of AI chatbots for well-being with their lifestyle, and older people are influenced by social factors to use them. Higher complexity can be an obstacle for AI chatbots for well-being use.

AB - The global mental health sector lacks resources particularly in low- and middle-income countries. AI- chatbots are increasingly recognized as a promising resource to support mental health. However, the acceptance of AI chatbots in the field of mental health is still low. Our study aims to predict their usage, identifying the features which are more relevant for the prediction. An online survey was created in China with 400 valid responses collected. For our prediction exercise we used three Machine Learning algorithms: decision tree, logistic regression, and random forest. The accuracy of these algorithms ranged from 64-71%. Age was the most important feature to explain usage. Younger people value the compatibility of AI chatbots for well-being with their lifestyle, and older people are influenced by social factors to use them. Higher complexity can be an obstacle for AI chatbots for well-being use.

KW - Artificial Intelligence

KW - Mental Health

KW - AI chatbots

KW - Machine Learning

KW - Technology Adoption

UR - https://www.scopus.com/pages/publications/105041133315

U2 - 10.1016/j.procs.2026.03.112

DO - 10.1016/j.procs.2026.03.112

M3 - Conference article

SN - 1877-0509

VL - 278

SP - 1291

EP - 1298

JO - Procedia Computer Science

JF - Procedia Computer Science

Y2 - 26 November 2025 through 28 November 2025

ER -

AI Chatbots for Well-Being Adoption Drivers: A Machine Learning Approach

Abstract

UN SDGs

Keywords

Access to Document

Other files and links

Fingerprint

Cite this