Extracting psychiatric stressors for suicide from social media using deep learning

Abstract Background Suicide has been one of the leading causes of deaths in the United States. One major cause of suicide is psychiatric stressors. The detection of psychiatric stressors in an at risk population will facilitate the early prevention of suicidal behaviors and suicide. In recent years,...

Full description

Bibliographic Details
Main Authors: Jingcheng Du, Yaoyun Zhang, Jianhong Luo, Yuxi Jia, Qiang Wei, Cui Tao, Hua Xu
Format: Article
Language:English
Published: BMC 2018-07-01
Series:BMC Medical Informatics and Decision Making
Subjects:
Online Access:http://link.springer.com/article/10.1186/s12911-018-0632-8
_version_ 1818849848379572224
author Jingcheng Du
Yaoyun Zhang
Jianhong Luo
Yuxi Jia
Qiang Wei
Cui Tao
Hua Xu
author_facet Jingcheng Du
Yaoyun Zhang
Jianhong Luo
Yuxi Jia
Qiang Wei
Cui Tao
Hua Xu
author_sort Jingcheng Du
collection DOAJ
description Abstract Background Suicide has been one of the leading causes of deaths in the United States. One major cause of suicide is psychiatric stressors. The detection of psychiatric stressors in an at risk population will facilitate the early prevention of suicidal behaviors and suicide. In recent years, the widespread popularity and real-time information sharing flow of social media allow potential early intervention in a large-scale population. However, few automated approaches have been proposed to extract psychiatric stressors from Twitter. The goal of this study was to investigate techniques for recognizing suicide related psychiatric stressors from Twitter using deep learning based methods and transfer learning strategy which leverages an existing annotation dataset from clinical text. Methods First, a dataset of suicide-related tweets was collected from Twitter streaming data with a multiple-step pipeline including keyword-based retrieving, filtering and further refining using an automated binary classifier. Specifically, a convolutional neural networks (CNN) based algorithm was used to build the binary classifier. Next, psychiatric stressors were annotated in the suicide-related tweets. The stressor recognition problem is conceptualized as a typical named entity recognition (NER) task and tackled using recurrent neural networks (RNN) based methods. Moreover, to reduce the annotation cost and improve the performance, transfer learning strategy was adopted by leveraging existing annotation from clinical text. Results & conclusions To our best knowledge, this is the first effort to extract psychiatric stressors from Twitter data using deep learning based approaches. Comparison to traditional machine learning algorithms shows the superiority of deep learning based approaches. CNN is leading the performance at identifying suicide-related tweets with a precision of 78% and an F-1 measure of 83%, outperforming Support Vector Machine (SVM), Extra Trees (ET), etc. RNN based psychiatric stressors recognition obtains the best F-1 measure of 53.25% by exact match and 67.94% by inexact match, outperforming Conditional Random Fields (CRF). Moreover, transfer learning from clinical notes for the Twitter corpus outperforms the training with Twitter corpus only with an F-1 measure of 54.9% by exact match. The results indicate the advantages of deep learning based methods for the automated stressors recognition from social media.
first_indexed 2024-12-19T06:39:45Z
format Article
id doaj.art-1c11b4c9f0a747688ab035d7d6660d98
institution Directory Open Access Journal
issn 1472-6947
language English
last_indexed 2024-12-19T06:39:45Z
publishDate 2018-07-01
publisher BMC
record_format Article
series BMC Medical Informatics and Decision Making
spelling doaj.art-1c11b4c9f0a747688ab035d7d6660d982022-12-21T20:32:06ZengBMCBMC Medical Informatics and Decision Making1472-69472018-07-0118S2778710.1186/s12911-018-0632-8Extracting psychiatric stressors for suicide from social media using deep learningJingcheng Du0Yaoyun Zhang1Jianhong Luo2Yuxi Jia3Qiang Wei4Cui Tao5Hua Xu6The University of Texas School of Biomedical InformaticsThe University of Texas School of Biomedical InformaticsThe University of Texas School of Biomedical InformaticsThe University of Texas School of Biomedical InformaticsThe University of Texas School of Biomedical InformaticsThe University of Texas School of Biomedical InformaticsThe University of Texas School of Biomedical InformaticsAbstract Background Suicide has been one of the leading causes of deaths in the United States. One major cause of suicide is psychiatric stressors. The detection of psychiatric stressors in an at risk population will facilitate the early prevention of suicidal behaviors and suicide. In recent years, the widespread popularity and real-time information sharing flow of social media allow potential early intervention in a large-scale population. However, few automated approaches have been proposed to extract psychiatric stressors from Twitter. The goal of this study was to investigate techniques for recognizing suicide related psychiatric stressors from Twitter using deep learning based methods and transfer learning strategy which leverages an existing annotation dataset from clinical text. Methods First, a dataset of suicide-related tweets was collected from Twitter streaming data with a multiple-step pipeline including keyword-based retrieving, filtering and further refining using an automated binary classifier. Specifically, a convolutional neural networks (CNN) based algorithm was used to build the binary classifier. Next, psychiatric stressors were annotated in the suicide-related tweets. The stressor recognition problem is conceptualized as a typical named entity recognition (NER) task and tackled using recurrent neural networks (RNN) based methods. Moreover, to reduce the annotation cost and improve the performance, transfer learning strategy was adopted by leveraging existing annotation from clinical text. Results & conclusions To our best knowledge, this is the first effort to extract psychiatric stressors from Twitter data using deep learning based approaches. Comparison to traditional machine learning algorithms shows the superiority of deep learning based approaches. CNN is leading the performance at identifying suicide-related tweets with a precision of 78% and an F-1 measure of 83%, outperforming Support Vector Machine (SVM), Extra Trees (ET), etc. RNN based psychiatric stressors recognition obtains the best F-1 measure of 53.25% by exact match and 67.94% by inexact match, outperforming Conditional Random Fields (CRF). Moreover, transfer learning from clinical notes for the Twitter corpus outperforms the training with Twitter corpus only with an F-1 measure of 54.9% by exact match. The results indicate the advantages of deep learning based methods for the automated stressors recognition from social media.http://link.springer.com/article/10.1186/s12911-018-0632-8SuicideMental healthPsychiatric stressorsSocial mediaDeep learningNamed entity recognition
spellingShingle Jingcheng Du
Yaoyun Zhang
Jianhong Luo
Yuxi Jia
Qiang Wei
Cui Tao
Hua Xu
Extracting psychiatric stressors for suicide from social media using deep learning
BMC Medical Informatics and Decision Making
Suicide
Mental health
Psychiatric stressors
Social media
Deep learning
Named entity recognition
title Extracting psychiatric stressors for suicide from social media using deep learning
title_full Extracting psychiatric stressors for suicide from social media using deep learning
title_fullStr Extracting psychiatric stressors for suicide from social media using deep learning
title_full_unstemmed Extracting psychiatric stressors for suicide from social media using deep learning
title_short Extracting psychiatric stressors for suicide from social media using deep learning
title_sort extracting psychiatric stressors for suicide from social media using deep learning
topic Suicide
Mental health
Psychiatric stressors
Social media
Deep learning
Named entity recognition
url http://link.springer.com/article/10.1186/s12911-018-0632-8
work_keys_str_mv AT jingchengdu extractingpsychiatricstressorsforsuicidefromsocialmediausingdeeplearning
AT yaoyunzhang extractingpsychiatricstressorsforsuicidefromsocialmediausingdeeplearning
AT jianhongluo extractingpsychiatricstressorsforsuicidefromsocialmediausingdeeplearning
AT yuxijia extractingpsychiatricstressorsforsuicidefromsocialmediausingdeeplearning
AT qiangwei extractingpsychiatricstressorsforsuicidefromsocialmediausingdeeplearning
AT cuitao extractingpsychiatricstressorsforsuicidefromsocialmediausingdeeplearning
AT huaxu extractingpsychiatricstressorsforsuicidefromsocialmediausingdeeplearning