Tracking Suicide Risk Factors Through Twitter in the US

Jashinsky, Jared; Burton, Scott H.; Hanson, Carl L.; West, Josh; Giraud‐Carrier, Christophe; Barnes, Michael; Argyle, Trenton

doi:10.1027/0227-5910/a000234

Cited by 318 publications

(263 citation statements)

References 17 publications

(21 reference statements)

Supporting

Mentioning

256

Contrasting

Unclassified

Order By: Relevance

“…The automatic detection of suicidal ideation in social networks and forums provide a powerful tool to address early interventions in serious situations. Additionally, these techniques allow tracking the prevalence of different suicide risk factors among the population (Jashinsky et al, 2014;Fodeh et al, 2017), which provides valuable information that can be capitalized for the design of prevention plans.…”

Section: Introductionmentioning

confidence: 99%

Using contextual information for automatic triage of posts in a peer-support forum

Altszyler¹,

Berenstein²,

Milne³

et al. 2018

Proceedings of the Fifth Workshop on Computational Linguistics And Clinical Psychology: From Keyboard to Clinic

View full text Add to dashboard Cite

Mental health forums are online spaces where people can share their experiences anonymously and get peer support. These forums, require the supervision of moderators to provide support in delicate cases, such as posts expressing suicide ideation. The large increase in the number of forum users makes the task of the moderators unmanageable without the help of automatic triage systems. In the present paper, we present a Machine Learning approach for the triage of posts. Most approaches in the literature focus on the content of the posts, but only a few authors take advantage of features extracted from the context in which they appear. Our approach consists of the development and implementation of a large variety of new features from both, the content and the context of posts, such as previous messages, interaction with other users and author's history. Our method has competed in the CLPsych 2017 Shared Task, obtaining the first place for several of the subtasks. Moreover, we also found that models that take advantage of post context improve significantly its performance in the detection of flagged posts (posts that require moderators attention), as well as those that focus on post content outperforms in the detection of most urgent events.

show abstract

Section: Introductionmentioning

confidence: 99%

Using contextual information for automatic triage of posts in a peer-support forum

Altszyler¹,

Berenstein²,

Milne³

et al. 2018

Proceedings of the Fifth Workshop on Computational Linguistics And Clinical Psychology: From Keyboard to Clinic

View full text Add to dashboard Cite

show abstract

“…Cheng et al (2012) consider the ethical and political implications of online data collection for suicide prevention. Jashinsky et al (2013) show correlations between frequency in tweets related to suicide and actual suicide in the 50 United States of America. Sadilek et al (2014) (Wray et al, 2011), but most of this work was with respect to offline social systems.…”

Section: Related Workmentioning

confidence: 99%

“…Next, we adopted a collection of inclusive search terms/phrases from Jashinsky et al (2013), which was designed specifically for capturing tweets related to suicide risk factors, and applied them to our source corpus. We added to these more terms, from (Crosby et al, 2011) (see Table 2).…”

Section: Filtering Tweetsmentioning

confidence: 99%

Proceedings of the Workshop on Computational Linguistics and Clinical Psychology: From Linguistic Signal to Clinical Reality

2014

View full text Add to dashboard Cite

ii Introduction Mental health problems are among the costliest challenges we face, in every possible sense of cost. The numbers are staggering: to cite just a few, in the United States mental health spending accounted for $33 billion in 1986, $100 billion in 2003, and is projected to increase to $203 billion for 2014; some 25 million American adults will have an episode of major depression this year; and suicide is the third leading cause of death for people between 10 and 24 years old. The importance of clinical psychology as a problem space cannot be overstated.For clinical psychologists, language plays a central role in diagnosis. Indeed, many clinical instruments fundamentally rely on what is, in effect, manual annotation of patient language. Applying language technology in this domain, e.g. in language-based assessment, could potentially have an enormous impact, because many individuals are motivated to underreport psychiatric symptoms (consider active duty soldiers, for example) or lack the self-awareness to report accurately (consider individuals involved in substance abuse who do not recognize their own addiction), and because many people -e.g. those without adequate insurance or in rural areas -cannot even obtain access to a clinician who is qualified to perform a psychological evaluation. Bringing language technology to bear on these problems could potentially lead to inexpensive screening measures that could be administered by a wider array of healthcare professionals, which is particularly important since the majority of individuals who present with symptoms of mental health problems do so in a primary care physician's office. Given the burden on primary care physicians to diagnose mental health disorders in very little time, the American Academy of Family Physicians has recognized the need for diagnostic tools for physicians that are "suited to the realities of their practice".Although automated language analysis connected with mental health conditions goes back at least as far as the 1990s, it has not been a major focus for computational linguistics compared with other application domains. However, recently there has been noticable uptick in research activity on this topic. One recent shared task brings together research on the Big-5 personality traits, and another involved research on identification of emotion in suicide notes. Research has been done on language analysis in the context of, for example, autistic spectrum disorders, dementia, depression, post-partum depression, general life satisfaction , and suicide risk. This increase in attention is consistent with, and gains power from, the recent rise in computational linguistics activity connected with computational social science more broadly.With computational linguistics research on this topic moving toward critical mass, one key goal of this workshop was to bring together researchers to discuss the current state of the art, share methods, and set directions for the future. The workshop had a second goal also, though: to directly engage cli...

show abstract

“…This methodology has been used and explained in previous research [22,34]. Six Twitter accounts were purposefully sampled for either being very pro-ED or very open about having ED.…”

Section: Data Collectionmentioning

confidence: 99%

“…Several studies have used Twitter content to explore such conditions as depression and suicide [22,23], electronic cigarette use [24,25], tobacco use [26,27], alcohol use [28], influenza [29][30][31], and substance abuse [32,33].…”

mentioning

confidence: 99%

An Exploration of Eating Disorders and Emotional States: An Infodemiological Study of Tweets Among Followers of Pro-Eating Disorder Sites

Whitney¹,

Hovey²,

Partington³

et al. 2017

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

Tracking Suicide Risk Factors Through Twitter in the US

Abstract: Twitter may be a viable tool for real-time monitoring of suicide risk factors on a large scale. This study demonstrates that individuals who are at risk for suicide may be detected through social media.

Cited by 318 publications

References 17 publications

Using contextual information for automatic triage of posts in a peer-support forum

Using contextual information for automatic triage of posts in a peer-support forum

Proceedings of the Workshop on Computational Linguistics and Clinical Psychology: From Linguistic Signal to Clinical Reality

An Exploration of Eating Disorders and Emotional States: An Infodemiological Study of Tweets Among Followers of Pro-Eating Disorder Sites

Contact Info

Product

Resources

About