Mental Disorder and Suicidal Ideation Detection From Social Media Using Deep Neural Networks

dc.authorid Dehkharghani, Rahim/0000-0002-9619-8247
dc.authorscopusid 57219841474
dc.authorscopusid 24528505600
dc.authorwosid Ezerceli, Özay/AAY-9215-2021
dc.authorwosid Dehkharghani, Rahim/JXY-0317-2024
dc.contributor.author Ezerceli, Ozay
dc.contributor.author Dehkharghani, Rahim
dc.contributor.author Dehkharghani, Rahim
dc.contributor.other Computer Engineering
dc.date.accessioned 2024-10-15T19:40:58Z
dc.date.available 2024-10-15T19:40:58Z
dc.date.issued 2024
dc.department Kadir Has University en_US
dc.department-temp [Ezerceli, Ozay] Isik Univ, Comp Engn, TR-34980 Istanbul, Turkiye; [Dehkharghani, Rahim] Kadir Has Univ, Management Informat Syst & Comp Engn Dept, Cibali Campus, TR-34083 Istanbul, Turkiye en_US
dc.description Dehkharghani, Rahim/0000-0002-9619-8247 en_US
dc.description.abstract Depression and suicidal ideation are global reasons for life-threatening injury and death. Mental disorders have increased especially among young people in recent years, and early detection of those cases can prevent suicide attempts. Social media platforms provide users with an anonymous space to interact with others, making them a secure environment to discuss their mental disorders. This paper proposes a solution to detect depression/suicidal ideation using natural language processing and deep learning techniques. We used Transformers and a unique model to train the proposed model and applied it to three different datasets: SuicideDetection, CEASEv2.0, and SWMH. The proposed model is evaluated using the accuracy, precision, recall, and ROC curve. The proposed model outperforms the state-of-the-art in the SuicideDetection and CEASEv2.0 datasets, achieving F1 scores of 0.97 and 0.75, respectively. However, in the SWMH data set, the proposed model is 4% points behind the state-of-the-art precision providing the F1 score of 0.68. In the real world, this project could help psychologists in the early detection of depression and suicidal ideation for a more efficient treatment. The proposed model achieves state-of-the-art performance in two of the three datasets, so they could be used to develop a screening tool that could be used by mental health professionals or individuals to assess their own risk of suicide. This could lead to early intervention and treatment, which could save lives. en_US
dc.description.sponsorship Scientific and Technological Research Council of Turkiye (TUBIdot;TAK) en_US
dc.description.sponsorship Open access funding provided by the Scientific and Technological Research Council of Turkiye (TUB & Idot;TAK). en_US
dc.description.woscitationindex Emerging Sources Citation Index
dc.identifier.citationcount 0
dc.identifier.doi 10.1007/s42001-024-00307-1
dc.identifier.issn 2432-2717
dc.identifier.issn 2432-2725
dc.identifier.scopus 2-s2.0-85197700231
dc.identifier.scopusquality Q2
dc.identifier.uri https://doi.org/10.1007/s42001-024-00307-1
dc.identifier.uri https://hdl.handle.net/20.500.12469/6401
dc.identifier.wos WOS:001263428000002
dc.language.iso en en_US
dc.publisher Springernature en_US
dc.relation.publicationcategory Makale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanı en_US
dc.rights info:eu-repo/semantics/openAccess en_US
dc.scopus.citedbyCount 5
dc.subject Suicidal ideation detection en_US
dc.subject Social media content en_US
dc.subject Word embedding en_US
dc.subject Deep neural network en_US
dc.subject BERT transformers en_US
dc.title Mental Disorder and Suicidal Ideation Detection From Social Media Using Deep Neural Networks en_US
dc.type Article en_US
dc.wos.citedbyCount 4
dspace.entity.type Publication
relation.isAuthorOfPublication c9d03199-34e8-4420-bce7-6ee3b85deb19
relation.isAuthorOfPublication.latestForDiscovery c9d03199-34e8-4420-bce7-6ee3b85deb19
relation.isOrgUnitOfPublication fd8e65fe-c3b3-4435-9682-6cccb638779c
relation.isOrgUnitOfPublication.latestForDiscovery fd8e65fe-c3b3-4435-9682-6cccb638779c

Files