File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Article: Developing and validating a parser-based suicidality detection model in text-based mental health services

TitleDeveloping and validating a parser-based suicidality detection model in text-based mental health services
Authors
KeywordsDependency parser
False alarms
Mental health services
Suicidal ideation
Suicide prevention
Text mining
Issue Date2023
Citation
Journal of Affective Disorders, 2023, v. 335, p. 228-232 How to Cite?
AbstractBackground: Advances in text-mining can potentially aid online text-based mental health services in detecting suicidality. However, false positive remains a challenge. Methods: Data of a free 24/7 online text-based counseling service in Hong Kong were used to develop a novel parser-based algorithm (PBSD) to detect suicidal ideation while minimizing false alarms. Sessions containing keywords related to suicidality were extracted (N = 1267). PBSD first applies a sentence parser to work out the grammatical structure of each sentence, including subject, object, dependent and modifier. Then a set of syntax rules were applied to judge if a flagged sentence is a true or false positive. Half of the sessions were randomly selected to train PBSD, the remaining were used as the test set. A standard keywords matching model was adopted as the baseline comparison. Accuracy and recall were reported to demonstrate models' performance. Results: Of the 1267 sessions, 585 (46.2 %) were false alarms. The false alarms were categorized into four types: negation-induced false alarms (NIFA; 14 %), subject-induced false alarms (SIFA; 19 %), tense-induced false alarms (TIFA; 30 %), and other types of false alarms (OTFA; 37 %). PBSD significantly outperforms the baseline keywords matching model on accuracy (0.68 vs 0.53, 28.3 %). It successfully amended 36.8 % (105/297) lexicon matching-caused false alarms. The reduction on recall was marginal (1 vs 0.96, 4 %). Conclusions: The proposed model significantly improves the use of lexicon-based method by reducing false alarms and improving the accuracy of suicidality detection. It can potentially reduce unnecessary panic and distraction caused by false alarms among frontline service-providers.
Persistent Identifierhttp://hdl.handle.net/10722/330313
ISSN
2023 Impact Factor: 4.9
2023 SCImago Journal Rankings: 2.082
ISI Accession Number ID

 

DC FieldValueLanguage
dc.contributor.authorXu, Zhongzhi-
dc.contributor.authorChan, Christian S.-
dc.contributor.authorFung, Jerry-
dc.contributor.authorTsang, Christy-
dc.contributor.authorZhang, Qingpeng-
dc.contributor.authorXu, Yucan-
dc.contributor.authorCheung, Florence-
dc.contributor.authorCheng, Weibin-
dc.contributor.authorChan, Evangeline-
dc.contributor.authorYip, Paul S.F.-
dc.date.accessioned2023-09-05T12:09:31Z-
dc.date.available2023-09-05T12:09:31Z-
dc.date.issued2023-
dc.identifier.citationJournal of Affective Disorders, 2023, v. 335, p. 228-232-
dc.identifier.issn0165-0327-
dc.identifier.urihttp://hdl.handle.net/10722/330313-
dc.description.abstractBackground: Advances in text-mining can potentially aid online text-based mental health services in detecting suicidality. However, false positive remains a challenge. Methods: Data of a free 24/7 online text-based counseling service in Hong Kong were used to develop a novel parser-based algorithm (PBSD) to detect suicidal ideation while minimizing false alarms. Sessions containing keywords related to suicidality were extracted (N = 1267). PBSD first applies a sentence parser to work out the grammatical structure of each sentence, including subject, object, dependent and modifier. Then a set of syntax rules were applied to judge if a flagged sentence is a true or false positive. Half of the sessions were randomly selected to train PBSD, the remaining were used as the test set. A standard keywords matching model was adopted as the baseline comparison. Accuracy and recall were reported to demonstrate models' performance. Results: Of the 1267 sessions, 585 (46.2 %) were false alarms. The false alarms were categorized into four types: negation-induced false alarms (NIFA; 14 %), subject-induced false alarms (SIFA; 19 %), tense-induced false alarms (TIFA; 30 %), and other types of false alarms (OTFA; 37 %). PBSD significantly outperforms the baseline keywords matching model on accuracy (0.68 vs 0.53, 28.3 %). It successfully amended 36.8 % (105/297) lexicon matching-caused false alarms. The reduction on recall was marginal (1 vs 0.96, 4 %). Conclusions: The proposed model significantly improves the use of lexicon-based method by reducing false alarms and improving the accuracy of suicidality detection. It can potentially reduce unnecessary panic and distraction caused by false alarms among frontline service-providers.-
dc.languageeng-
dc.relation.ispartofJournal of Affective Disorders-
dc.subjectDependency parser-
dc.subjectFalse alarms-
dc.subjectMental health services-
dc.subjectSuicidal ideation-
dc.subjectSuicide prevention-
dc.subjectText mining-
dc.titleDeveloping and validating a parser-based suicidality detection model in text-based mental health services-
dc.typeArticle-
dc.description.naturelink_to_subscribed_fulltext-
dc.identifier.doi10.1016/j.jad.2023.04.128-
dc.identifier.pmid37150217-
dc.identifier.scopuseid_2-s2.0-85159414802-
dc.identifier.volume335-
dc.identifier.spage228-
dc.identifier.epage232-
dc.identifier.eissn1573-2517-
dc.identifier.isiWOS:000998465700001-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats