Learning Models for Suicide Prediction from Social Media Posts

Ning Wang; Fan Luo; Yuvraj Shivtare; Varsha Badal; K. P. Subbalakshmi; R. Chandramouli; Ellen Lee

Learning Models for Suicide Prediction from Social Media Posts

Ning Wang
, Fan Luo
, Yuvraj Shivtare
, Varsha Badal
, K. P. Subbalakshmi
, R. Chandramouli
, Ellen Lee

Department of Electrical and Computer Engineering

Stevens Institute of Technology
University of California at San Diego

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

17 Scopus citations

Abstract

We propose a deep learning architecture and test three other machine learning models to automatically detect individuals that will attempt suicide within (1) 30 days and (2) six months, using their social media post data provided in (Macavaney et al., 2021) via the CLPsych 2021 shared task. Additionally, we create and extract three sets of handcrafted features for suicide risk detection based on the three-stage theory of suicide and prior work on emotions and the use of pronouns among persons exhibiting suicidal ideations. Extensive experimentations show that some of the traditional machine learning methods outperform the baseline with an F1 score of 0.741 and F2 score of 0.833 on subtask 1 (prediction of a suicide attempt 30 days prior). However, the proposed deep learning method outperforms the baseline with F1 score of 0.737 and F2 score of 0.843 on subtask 2 (prediction of suicide 6 months prior).

Original language	English
Title of host publication	Computational Linguistics and Clinical Psychology
Subtitle of host publication	Improving Access, CLPsych 2021 - Proceedings of the 7th Workshop, in conjunction with NAACL 2021
Editors	Nazli Goharian, Philip Resnik, Andrew Yates, Molly Ireland, Kate Niederhoffer, Rebecca Resnik
Pages	87-92
Number of pages	6
ISBN (Electronic)	9781954085411
State	Published - 2021
Event	7th Workshop on Computational Linguistics and Clinical Psychology: Improving Access, CLPsych 2021 - Virtual, Online Duration: 11 Jun 2021 → …

Publication series

Name	Computational Linguistics and Clinical Psychology: Improving Access, CLPsych 2021 - Proceedings of the 7th Workshop, in conjunction with NAACL 2021

Conference

Conference	7th Workshop on Computational Linguistics and Clinical Psychology: Improving Access, CLPsych 2021
City	Virtual, Online
Period	11/06/21 → …

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 3 Good Health and Well-being

Cite this

Wang, N., Luo, F., Shivtare, Y., Badal, V., Subbalakshmi, K. P., Chandramouli, R., & Lee, E. (2021). Learning Models for Suicide Prediction from Social Media Posts. In N. Goharian, P. Resnik, A. Yates, M. Ireland, K. Niederhoffer, & R. Resnik (Eds.), Computational Linguistics and Clinical Psychology: Improving Access, CLPsych 2021 - Proceedings of the 7th Workshop, in conjunction with NAACL 2021 (pp. 87-92). (Computational Linguistics and Clinical Psychology: Improving Access, CLPsych 2021 - Proceedings of the 7th Workshop, in conjunction with NAACL 2021).

Wang, Ning ; Luo, Fan ; Shivtare, Yuvraj et al. / Learning Models for Suicide Prediction from Social Media Posts. Computational Linguistics and Clinical Psychology: Improving Access, CLPsych 2021 - Proceedings of the 7th Workshop, in conjunction with NAACL 2021. editor / Nazli Goharian ; Philip Resnik ; Andrew Yates ; Molly Ireland ; Kate Niederhoffer ; Rebecca Resnik. 2021. pp. 87-92 (Computational Linguistics and Clinical Psychology: Improving Access, CLPsych 2021 - Proceedings of the 7th Workshop, in conjunction with NAACL 2021).

@inproceedings{a19d385b66814f5a996e0ed410fd3c57,

title = "Learning Models for Suicide Prediction from Social Media Posts",

abstract = "We propose a deep learning architecture and test three other machine learning models to automatically detect individuals that will attempt suicide within (1) 30 days and (2) six months, using their social media post data provided in (Macavaney et al., 2021) via the CLPsych 2021 shared task. Additionally, we create and extract three sets of handcrafted features for suicide risk detection based on the three-stage theory of suicide and prior work on emotions and the use of pronouns among persons exhibiting suicidal ideations. Extensive experimentations show that some of the traditional machine learning methods outperform the baseline with an F1 score of 0.741 and F2 score of 0.833 on subtask 1 (prediction of a suicide attempt 30 days prior). However, the proposed deep learning method outperforms the baseline with F1 score of 0.737 and F2 score of 0.843 on subtask 2 (prediction of suicide 6 months prior).",

author = "Ning Wang and Fan Luo and Yuvraj Shivtare and Varsha Badal and Subbalakshmi, \{K. P.\} and R. Chandramouli and Ellen Lee",

note = "Publisher Copyright: {\textcopyright}2021 Association for Computational Linguistics.; 7th Workshop on Computational Linguistics and Clinical Psychology: Improving Access, CLPsych 2021 ; Conference date: 11-06-2021",

year = "2021",

language = "English",

series = "Computational Linguistics and Clinical Psychology: Improving Access, CLPsych 2021 - Proceedings of the 7th Workshop, in conjunction with NAACL 2021",

pages = "87--92",

editor = "Nazli Goharian and Philip Resnik and Andrew Yates and Molly Ireland and Kate Niederhoffer and Rebecca Resnik",

booktitle = "Computational Linguistics and Clinical Psychology",

}

Wang, N, Luo, F, Shivtare, Y, Badal, V, Subbalakshmi, KP, Chandramouli, R & Lee, E 2021, Learning Models for Suicide Prediction from Social Media Posts. in N Goharian, P Resnik, A Yates, M Ireland, K Niederhoffer & R Resnik (eds), Computational Linguistics and Clinical Psychology: Improving Access, CLPsych 2021 - Proceedings of the 7th Workshop, in conjunction with NAACL 2021. Computational Linguistics and Clinical Psychology: Improving Access, CLPsych 2021 - Proceedings of the 7th Workshop, in conjunction with NAACL 2021, pp. 87-92, 7th Workshop on Computational Linguistics and Clinical Psychology: Improving Access, CLPsych 2021, Virtual, Online, 11/06/21.

Learning Models for Suicide Prediction from Social Media Posts. / Wang, Ning; Luo, Fan; Shivtare, Yuvraj et al.
Computational Linguistics and Clinical Psychology: Improving Access, CLPsych 2021 - Proceedings of the 7th Workshop, in conjunction with NAACL 2021. ed. / Nazli Goharian; Philip Resnik; Andrew Yates; Molly Ireland; Kate Niederhoffer; Rebecca Resnik. 2021. p. 87-92 (Computational Linguistics and Clinical Psychology: Improving Access, CLPsych 2021 - Proceedings of the 7th Workshop, in conjunction with NAACL 2021).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Learning Models for Suicide Prediction from Social Media Posts

AU - Wang, Ning

AU - Luo, Fan

AU - Shivtare, Yuvraj

AU - Badal, Varsha

AU - Subbalakshmi, K. P.

AU - Chandramouli, R.

AU - Lee, Ellen

PY - 2021

Y1 - 2021

N2 - We propose a deep learning architecture and test three other machine learning models to automatically detect individuals that will attempt suicide within (1) 30 days and (2) six months, using their social media post data provided in (Macavaney et al., 2021) via the CLPsych 2021 shared task. Additionally, we create and extract three sets of handcrafted features for suicide risk detection based on the three-stage theory of suicide and prior work on emotions and the use of pronouns among persons exhibiting suicidal ideations. Extensive experimentations show that some of the traditional machine learning methods outperform the baseline with an F1 score of 0.741 and F2 score of 0.833 on subtask 1 (prediction of a suicide attempt 30 days prior). However, the proposed deep learning method outperforms the baseline with F1 score of 0.737 and F2 score of 0.843 on subtask 2 (prediction of suicide 6 months prior).

AB - We propose a deep learning architecture and test three other machine learning models to automatically detect individuals that will attempt suicide within (1) 30 days and (2) six months, using their social media post data provided in (Macavaney et al., 2021) via the CLPsych 2021 shared task. Additionally, we create and extract three sets of handcrafted features for suicide risk detection based on the three-stage theory of suicide and prior work on emotions and the use of pronouns among persons exhibiting suicidal ideations. Extensive experimentations show that some of the traditional machine learning methods outperform the baseline with an F1 score of 0.741 and F2 score of 0.833 on subtask 1 (prediction of a suicide attempt 30 days prior). However, the proposed deep learning method outperforms the baseline with F1 score of 0.737 and F2 score of 0.843 on subtask 2 (prediction of suicide 6 months prior).

UR - https://www.scopus.com/pages/publications/85123219530

UR - https://www.scopus.com/pages/publications/85123219530#tab=citedBy

M3 - Conference contribution

AN - SCOPUS:85123219530

T3 - Computational Linguistics and Clinical Psychology: Improving Access, CLPsych 2021 - Proceedings of the 7th Workshop, in conjunction with NAACL 2021

SP - 87

EP - 92

BT - Computational Linguistics and Clinical Psychology

A2 - Goharian, Nazli

A2 - Resnik, Philip

A2 - Yates, Andrew

A2 - Ireland, Molly

A2 - Niederhoffer, Kate

A2 - Resnik, Rebecca

T2 - 7th Workshop on Computational Linguistics and Clinical Psychology: Improving Access, CLPsych 2021

Y2 - 11 June 2021

ER -

Wang N, Luo F, Shivtare Y, Badal V, Subbalakshmi KP, Chandramouli R et al. Learning Models for Suicide Prediction from Social Media Posts. In Goharian N, Resnik P, Yates A, Ireland M, Niederhoffer K, Resnik R, editors, Computational Linguistics and Clinical Psychology: Improving Access, CLPsych 2021 - Proceedings of the 7th Workshop, in conjunction with NAACL 2021. 2021. p. 87-92. (Computational Linguistics and Clinical Psychology: Improving Access, CLPsych 2021 - Proceedings of the 7th Workshop, in conjunction with NAACL 2021).

Learning Models for Suicide Prediction from Social Media Posts

Abstract

Publication series

Conference

UN SDGs

Other files and links

Fingerprint

Cite this