Search

As online mental health support groups become increasingly popular, they require more support from volunteers and trained moderators who help their users through "interventions" (i.e., responding to questions and providing support). We present a system that supports such human interventions using Natural Language Generation (NLG) techniques. The system generates draft responses aimed at reducing moderators' workload, and improving their efficacy. NLG and human interventions were compared through the ratings of 35 psychology interns. The NLG-based system was capable of generating messages that are grammatically correct with clear language. The system needs improvement, however, moderators can already use it as draft responses. [ABSTRACT FROM AUTHOR]

Background: The Mental Health eClinic (MHeC) aims to deliver best-practice clinical services to young people experiencing mental health problems by making clinical care accessible, affordable, and available to young people whenever and wherever they need it most. The original MHeC consists of home page with a visible triage system for those requiring urgent help; a online physical and mental health self-report assessment; a results dashboard; a booking and videoconferencing system; and the generation of a personalized well-being plan. Populations who do not speak English and reside in English-speaking countries are less likely to receive mental health care. In Australia, international students have been identified as disadvantaged compared with their peers; have weaker social support networks; and have higher rates of psychological distress. This scenario is acquiring significant relevance as Spanish-speaking migration is rapidly growing in Australia, and the mental health services for culturally and linguistically diverse populations are limited. Having a Spanish version (MHeC-S) of the Mental Health eClinic would greatly benefit these students.Objective: We used participatory design methodologies with users (young people aged 16-30 years, supportive others, and health professionals) to (1) conduct workshops with users to co-design and culturally adapt the MHeC; (2) inform the development of the MHeC-S alpha prototype; (3) test the usability of the MHeC-S alpha prototype; (4) translate, culturally adapt, and face-validate the MHeC-S self-report assessment; and (5) collect information to inform its beta prototype.Methods: A research and development cycle included several participatory design phases: co-design workshops; knowledge translation; language translation and cultural adaptation; and rapid prototyping and user testing of the MHeC-S alpha prototype.Results: We held 2 co-design workshops with 17 users (10 young people, 7 health professionals). A total of 15 participated in the one-on-one user testing sessions (7 young people, 5 health professionals, 3 supportive others). We collected 225 source documents, and thematic analysis resulted in 5 main themes (help-seeking barriers, technology platform, functionality, content, and user interface). A random sample of 106 source documents analyzed by 2 independent raters revealed almost perfect agreement for functionality (kappa=.86; P<.001) and content (kappa=.92; P<.001) and substantial agreement for the user interface (kappa=.785; P<.001). In this random sample, no annotations were coded for help-seeking barriers or the technology platform. Language was identified as the main barrier to getting medical or psychological services, and smartphones were the most-used device to access the internet. Acceptability was adequate for the prototype's 5 main elements: home page and triage system, self-report assessment, dashboard of results, booking and video visit system, and personalized well-being plan. The data also revealed gaps in the alpha prototype, such as the need for tailored assessment tools and a greater integration with Spanish-speaking services and communities. Spanish-language apps and e-tools, as well as online mental health information, were lacking.Conclusions: Through a research and development process, we co-designed and culturally adapted, developed and user tested, and evaluated the MHeC-S. By translating and culturally adapting the MHeC to Spanish, we aimed to increase accessibility and availability of e-mental health care in the developing world, and assist vulnerable populations that have migrated to English-speaking countries. [ABSTRACT FROM AUTHOR]