Proceedings of the Third Workshop on Computational Lingusitics And Clinical Psychology 2016
DOI: 10.18653/v1/w16-0312
|View full text |Cite
|
Sign up to set email alerts
|

CLPsych 2016 Shared Task: Triaging content in online peer-support forums

Abstract: This paper introduces a new shared task for the text mining community. It aims to directly support the moderators of a youth mental health forum by asking participants to automatically triage posts into one of four severity labels: green, amber, red or crisis. The task attracted 60 submissions from 15 different teams, the best of whom achieve scores well above baselines. Their approaches and results provide valuable insights to enable moderators of peer support forums to react quickly to the most urgent, conce… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

1
85
0
1

Year Published

2017
2017
2021
2021

Publication Types

Select...
4
3
1

Relationship

1
7

Authors

Journals

citations
Cited by 72 publications
(87 citation statements)
references
References 25 publications
1
85
0
1
Order By: Relevance
“…Homan et al (2014) and O'Dea et al (2015) detect posts containing suicide ideation and distress, and Li et al (2015) investigate unhelpful, stigmatizing reactions to suicide on the Chinese social media platform Weibo. Milne et al (2016) host a shared task for identifying and prioritizing concerning content on ReachOut.com's peer support forum.…”
Section: Nlp In Mental Health Applications 651 2 Methods and Overviewmentioning
confidence: 99%
See 1 more Smart Citation
“…Homan et al (2014) and O'Dea et al (2015) detect posts containing suicide ideation and distress, and Li et al (2015) investigate unhelpful, stigmatizing reactions to suicide on the Chinese social media platform Weibo. Milne et al (2016) host a shared task for identifying and prioritizing concerning content on ReachOut.com's peer support forum.…”
Section: Nlp In Mental Health Applications 651 2 Methods and Overviewmentioning
confidence: 99%
“…When the communities grow this becomes a challenge. The CLPsych 2016 shared task (Milne et al 2016) aimed to address such challenges of scale by allowing moderators to focus their efforts where it is most needed. It collected forum posts from ReachOut.com -a site for young Australians facing tough times -and asked participants to automatically triage them as green (no intervention required), amber (a moderator should ideally respond, but not urgently), red (a moderator should respond as soon as they can) or crisis (the post indicates someone is at risk of harm).…”
Section: Online Forums and Support Groupsmentioning
confidence: 99%
“…Through analysis of tweets posted by individuals attempting committing suicide, [19] indicate quantifiable signals of suicidal ideations. Moreover, the 2016 ACL Computational Linguistics and Clinical Psychology Workshop [20] defined a shared task on detecting the severity of the mental health forum posts. All of these studies define some discriminative features to classify depression in user-generated content in a message, for a user or at a community level.…”
Section: Related Workmentioning
confidence: 99%
“…Extracting features that best represent the social media text is a key step of such systems. A broad array of language representation and classification methods have been applied to triage on posts from the Australian mental health forum Reachout.com , which provides mental health information and support for youth online [14,15] . Recently, transfer learning has been used for text classification across a variety of contexts.…”
Section: Introductionmentioning
confidence: 99%