English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

With the advent of off-the-shelf intelligent home products and broaderinternet adoption, researchers increasingly explore smart computingapplications that provide easier access to health and wellness resources.AI-based systems like chatbots have the potential to provide services thatcould provide mental health support. However, existing therapy chatbots areoften retrieval-based, requiring users to respond with a constrained set ofanswers, which may not be appropriate given that such pre-determined inquiriesmay not reflect each patient's unique circumstances. Generative-basedapproaches, such as the OpenAI GPT models, could allow for more dynamicconversations in therapy chatbot contexts than previous approaches. Toinvestigate the generative-based model's potential in therapy chatbot contexts,we built a chatbot using the GPT-2 model. We fine-tuned it with 306 therapysession transcripts between family caregivers of individuals with dementia andtherapists conducting Problem Solving Therapy. We then evaluated the model'spre-trained and the fine-tuned model in terms of basic qualities using threemeta-information measurements: the proportion of non-word outputs, the lengthof response, and sentiment components. Results showed that: (1) the fine-tunedmodel created more non-word outputs than the pre-trained model; (2) thefine-tuned model generated outputs whose length was more similar to that of thetherapists compared to the pre-trained model; (3) both the pre-trained modeland fine-tuned model were likely to generate more negative and fewer positiveoutputs than the therapists. We discuss potential reasons for the problem, theimplications, and solutions for developing therapy chatbots and call forinvestigations of the AI-based system application.

An Evaluation of Generative Pre-Training Model-based Therapy Chatbot for Caregivers