Detecting Emotional Context for Safer Digital Mental Health Agents

aut.relation.endpage1443
aut.relation.journalStudies in Health Technology and Informatics
aut.relation.startpage1442
aut.relation.volume310
dc.contributor.authorChoi, Adi
dc.contributor.authorLi, Weihua
dc.contributor.authorWarren, Jim
dc.date.accessioned2024-02-07T23:10:11Z
dc.date.available2024-02-07T23:10:11Z
dc.date.issued2024-01-25
dc.description.abstractDigital tools for mental health show great promise, but concerns arise when they fail to recognize the user state. We train a classifier to detect the emotional context of dialogs among 6 categories, achieving 78% accuracy on top choice. Importantly greatest areas of confusion (excited-hopeful, angry-sad) are not of the most unsafe kind. Such a classifier could serve as a resource to the dialog managers of future digital mental health agents.
dc.identifier.citationStudies in Health Technology and Informatics, ISSN: 0926-9630 (Print); 0926-9630 (Online), IOS Press, 310, 1442-1443. doi: 10.3233/SHTI231235
dc.identifier.doi10.3233/SHTI231235
dc.identifier.issn0926-9630
dc.identifier.issn0926-9630
dc.identifier.urihttp://hdl.handle.net/10292/17204
dc.languageeng
dc.publisherIOS Press
dc.relation.urihttps://ebooks.iospress.nl/doi/10.3233/SHTI231235
dc.rights.accessrightsOpenAccess
dc.rights.urihttps://creativecommons.org/licenses/by-nc/4.0/deed.en_US
dc.subjectDialog agents
dc.subjectempathetic computing
dc.subjecte-therapy
dc.subjectmachine learning
dc.subjectDialog agents
dc.subjecte-therapy
dc.subjectempathetic computing
dc.subjectmachine learning
dc.subject4203 Health Services and Systems
dc.subject42 Health Sciences
dc.subjectMental Health
dc.subjectMental health
dc.subject3 Good Health and Well Being
dc.subject0807 Library and Information Studies
dc.subject1117 Public Health and Health Services
dc.subjectMedical Informatics
dc.subject4203 Health services and systems
dc.subject4601 Applied computing
dc.subject.meshDigital Health
dc.subject.meshEmotions
dc.subject.meshMental Health
dc.subject.meshMental Health
dc.subject.meshEmotions
dc.subject.meshDigital Health
dc.subject.meshMental Health
dc.subject.meshEmotions
dc.subject.meshDigital Health
dc.titleDetecting Emotional Context for Safer Digital Mental Health Agents
dc.typeJournal Article
pubs.elements-id537331
Files
Original bundle
Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
Detecting emotional context for safer digital mental health agents.pdf
Size:
134.11 KB
Format:
Adobe Portable Document Format
Description:
Journal article