Determining a Person's Suicide Risk by Voting on the Short-Term History of Tweets for the CLPsych 2021 Shared Task

Basit Öğe Kaydı
dc.authorid0000-0002-8150-4053en_US
dc.authorscopusid57195324891en_US
dc.authorwosidU-7459-2019en_US
dc.contributor.authorBayram, Ulya
dc.contributor.authorBenhiba, Lamia
dc.date.accessioned2022-08-01T11:00:09Z
dc.date.available2022-08-01T11:00:09Z
dc.date.issued2021en_US
dc.departmentFakülteler, Mühendislik Fakültesi, Elektrik-Elektronik Mühendisliği Bölümü
dc.description.abstractIn this shared task, we accept the challenge of constructing models to identify Twitter users who attempted suicide based on their tweets 30 and 182 days before the adverse event's occurrence. We explore multiple machine learning and deep learning methods to identify a person's suicide risk based on the short-term history of their tweets. Taking the real-life applicability of the model into account, we make the design choice of classifying on the tweet level. By voting the tweet-level suicide risk scores through an ensemble of classifiers, we predict the suicidal users 30-days before the event with an 81.8% true-positives rate. Meanwhile, the tweet-level voting falls short on the six-month-long data as the number of tweets with weak suicidal ideation levels weakens the overall suicidal signals in the long term.en_US
dc.description.sponsorshipUniversity of Maryland Institute for Advanced Computer Studies (UMIACS)en_US
dc.identifier.citationBayram, U., & Benhiba, L. (2021). Determining a person's suicide risk by voting on the short-term history of tweets for the CLPsych 2021 shared task. Paper presented at the Computational Linguistics and Clinical Psychology: Improving Access, CLPsych 2021 - Proceedings of the 7th Workshop, in Conjunction with NAACL 2021, 81-86.en_US
dc.identifier.endpage86en_US
dc.identifier.isbn9781954085411
dc.identifier.scopus2-s2.0-85111364845
dc.identifier.startpage81en_US
dc.identifier.urihttps://hdl.handle.net/20.500.12428/3637
dc.indekslendigikaynakScopus
dc.indekslendigikaynakPubMed
dc.institutionauthorBayram, Ulya
dc.language.isoen
dc.publisherAssociation for Computational Linguistics (ACL)en_US
dc.relation.ispartofComputational Linguistics and Clinical Psychology: Improving Access, CLPsych 2021 - Proceedings of the 7th Workshop, in conjunction with NAACL 2021en_US
dc.relation.publicationcategoryKonferans Öğesi - Uluslararası - Kurum Öğretim Elemanıen_US
dc.rightsinfo:eu-repo/semantics/closedAccessen_US
dc.subjectAdverse eventsen_US
dc.subjectConstructing modelsen_US
dc.subjectEnsemble of classifiersen_US
dc.subjectLearning methodsen_US
dc.subjectRisk scoreen_US
dc.subjectRisk-baseden_US
dc.subjectShort-term historyen_US
dc.subjectSuicidal ideationen_US
dc.subjectTrue positive ratesen_US
dc.titleDetermining a Person's Suicide Risk by Voting on the Short-Term History of Tweets for the CLPsych 2021 Shared Task
dc.typeConference Object

Dosyalar

Orijinal paket
Listeleniyor 1 - 1 / 1
[ X ]
İsim:
Ulya_Bayram_KonferansOgesi.pdf
Boyut:
131.5 KB
Biçim:
Adobe Portable Document Format
Açıklama:
Konferans Ögesi
İndir
Lisans paketi
Listeleniyor 1 - 1 / 1
[ X ]
İsim:
license.txt
Boyut:
1.44 KB
Biçim:
Item-specific license agreed upon to submission
Açıklama:
İndir

Koleksiyon

Scopus İndeksli Yayınlar Koleksiyonu
Dahili Tıp Bilimleri Bölümü Koleksiyonu
PubMed İndeksli Yayınlar Koleksiyonu