Search

Your search keyword '"natural language features"' showing total 3 results
Start Over Descriptor "natural language features"
3 results on '"natural language features"'

1. Chinese Mental Health Scale Translation

Author

Shan, Yi and Ji, Meng

Subjects
translation studies, sustainability, corpus linguistics, natural language features, statistics, thema EDItEUR::G Reference, Information and Interdisciplinary subjects::GT Interdisciplinary studies::GTC Communication studies, thema EDItEUR::C Language and Linguistics::CF Linguistics::CFP Translation and interpretation, thema EDItEUR::C Language and Linguistics::CF Linguistics::CFX Computational and corpus linguistics, thema EDItEUR::J Society and Social Sciences::JB Society and culture: general::JBC Cultural and media studies::JBCC Cultural studies::JBCC7 Cross-cultural / Intercultural studies and topics, thema EDItEUR::Q Philosophy and Religion::QR Religion and beliefs::QRA Religion: general
Abstract

This open access book illustrates the key steps and procedures of developing mental health scales into linguistically and culturally appropriate translations. Through illustrative case studies, we demonstrate that traditional forward and backward translation have significant methodological limitations when applied in mental health scale translation, such as linguistic and cultural inaccessibility and inaccuracy in the clinic. Our book will stimulate more academic debates and further systematic research into the significant, interdisciplinary area of mental health translation, which has been underexplored in Translation Studies.

Published
2024
Full Text
View/download PDF

2. Automatic Diagnosis of Mental Healthcare Information Actionability: Developing Binary Classifiers

Author

Meng Ji, Wenxiu Xie, Riliu Huang, and Xiaobo Qian

Subjects
Mental Health Services, Computer science, Health, Toxicology and Mutagenesis, Binary number, Machine learning, computer.software_genre, Article, Mental healthcare, Humans, mental healthcare, Interpretability, binary classification, business.industry, Public Health, Environmental and Occupational Health, Usability, Mental health, Readability, Mental Health, Binary classification, information quality assessment, Medicine, Artificial intelligence, Comprehension, business, actionability, Classifier (UML), computer, natural language features
Abstract

We aimed to develop a quantitative instrument to assist with the automatic evaluation of the actionability of mental healthcare information. We collected and classified two large sets of mental health information from certified mental health websites: generic and patient-specific mental healthcare information. We compared the performance of the optimised classifier with popular readability tools and non-optimised classifiers in predicting mental health information of high actionability for people with mental disorders. sensitivity of the classifier using both semantic and structural features as variables achieved statistically higher than that of the binary classifier using either semantic (p &lt, 0.001) or structural features (p = 0.0010). The specificity of the optimized classifier was statistically higher than that of the classifier using structural variables (p = 0.002) and the classifier using semantic variables (p = 0.001). Differences in specificity between the full-variable classifier and the optimised classifier were statistically insignificant (p = 0.687). These findings suggest the optimised classifier using as few as 19 semantic-structural variables was the best-performing classifier. By combining insights of linguistics and statistical analyses, we effectively increased the interpretability and the diagnostic utility of the binary classifiers to guide the development, evaluation of the actionability and usability of mental healthcare information.

Published
2021

3. Automatic Diagnosis of Mental Healthcare Information Actionability: Developing Binary Classifiers.

Author

Ji M, Xie W, Huang R, and Qian X

Subjects
Humans, Mental Health, Comprehension, Mental Health Services
Abstract

We aimed to develop a quantitative instrument to assist with the automatic evaluation of the actionability of mental healthcare information. We collected and classified two large sets of mental health information from certified mental health websites: generic and patient-specific mental healthcare information. We compared the performance of the optimised classifier with popular readability tools and non-optimised classifiers in predicting mental health information of high actionability for people with mental disorders. sensitivity of the classifier using both semantic and structural features as variables achieved statistically higher than that of the binary classifier using either semantic ( p < 0.001) or structural features ( p = 0.0010). The specificity of the optimized classifier was statistically higher than that of the classifier using structural variables ( p = 0.002) and the classifier using semantic variables ( p = 0.001). Differences in specificity between the full-variable classifier and the optimised classifier were statistically insignificant ( p = 0.687). These findings suggest the optimised classifier using as few as 19 semantic-structural variables was the best-performing classifier. By combining insights of linguistics and statistical analyses, we effectively increased the interpretability and the diagnostic utility of the binary classifiers to guide the development, evaluation of the actionability and usability of mental healthcare information.

Published
2021
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results