CLPsych 2015 Shared Task: Depression and PTSD on Twitter

Glen Coppersmith; Mark Dredze; Craig Harman; Kristy Hollingshead; Margaret Mitchell

CLPsych 2015 Shared Task: Depression and PTSD on Twitter

Glen Coppersmith, Mark Dredze, Craig Harman, Kristy Hollingshead, Margaret Mitchell

Whiting School of Engineering

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

Abstract

This paper presents a summary of the Computational Linguistics and Clinical Psychology (CLPsych) 2015 shared and unshared tasks. These tasks aimed to provide apples-to-apples comparisons of various approaches to modeling language relevant to mental health from social media. The data used for these tasks is from Twitter users who state a diagnosis of depression or post traumatic stress disorder (PTSD) and demographically-matched community controls. The unshared task was a hackathon held at Johns Hopkins University in November 2014 to explore the data, and the shared task was conducted remotely, with each participating team submitted scores for a held-back test set of users. The shared task consisted of three binary classification experiments: (1) depression versus control, (2) PTSD versus control, and (3) depression versus PTSD. Classifiers were compared primarily via their average precision, though a number of other metrics are used along with this to allow a more nuanced interpretation of the performance measures.

Original language	English (US)
Title of host publication	2nd Computational Linguistics and Clinical Psychology
Subtitle of host publication	From Linguistic Signal to Clinical Reality, CLPsych 2015 - Proceedings of the Workshop
Publisher	Association for Computational Linguistics (ACL)
Pages	31-39
Number of pages	9
ISBN (Electronic)	9781941643433
State	Published - 2015
Event	2nd Workshop on Computational Linguistics and Clinical Psychology: From Linguistic Signal to Clinical Reality, CLPsych 2015 - Denver, United States Duration: Jun 5 2015 → …

Publication series

Name	2nd Computational Linguistics and Clinical Psychology: From Linguistic Signal to Clinical Reality, CLPsych 2015 - Proceedings of the Workshop

Conference

Conference	2nd Workshop on Computational Linguistics and Clinical Psychology: From Linguistic Signal to Clinical Reality, CLPsych 2015
Country/Territory	United States
City	Denver
Period	6/5/15 → …

ASJC Scopus subject areas

Computational Theory and Mathematics
Language and Linguistics
Linguistics and Language
Clinical Psychology
Psychiatry and Mental health

Cite this

Coppersmith, G., Dredze, M., Harman, C., Hollingshead, K., & Mitchell, M. (2015). CLPsych 2015 Shared Task: Depression and PTSD on Twitter. In 2nd Computational Linguistics and Clinical Psychology: From Linguistic Signal to Clinical Reality, CLPsych 2015 - Proceedings of the Workshop (pp. 31-39). (2nd Computational Linguistics and Clinical Psychology: From Linguistic Signal to Clinical Reality, CLPsych 2015 - Proceedings of the Workshop). Association for Computational Linguistics (ACL).

CLPsych 2015 Shared Task: Depression and PTSD on Twitter. / Coppersmith, Glen; Dredze, Mark; Harman, Craig et al.
2nd Computational Linguistics and Clinical Psychology: From Linguistic Signal to Clinical Reality, CLPsych 2015 - Proceedings of the Workshop. Association for Computational Linguistics (ACL), 2015. p. 31-39 (2nd Computational Linguistics and Clinical Psychology: From Linguistic Signal to Clinical Reality, CLPsych 2015 - Proceedings of the Workshop).

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

Coppersmith, G, Dredze, M, Harman, C, Hollingshead, K & Mitchell, M 2015, CLPsych 2015 Shared Task: Depression and PTSD on Twitter. in 2nd Computational Linguistics and Clinical Psychology: From Linguistic Signal to Clinical Reality, CLPsych 2015 - Proceedings of the Workshop. 2nd Computational Linguistics and Clinical Psychology: From Linguistic Signal to Clinical Reality, CLPsych 2015 - Proceedings of the Workshop, Association for Computational Linguistics (ACL), pp. 31-39, 2nd Workshop on Computational Linguistics and Clinical Psychology: From Linguistic Signal to Clinical Reality, CLPsych 2015, Denver, United States, 6/5/15.

Coppersmith G, Dredze M, Harman C, Hollingshead K, Mitchell M. CLPsych 2015 Shared Task: Depression and PTSD on Twitter. In 2nd Computational Linguistics and Clinical Psychology: From Linguistic Signal to Clinical Reality, CLPsych 2015 - Proceedings of the Workshop. Association for Computational Linguistics (ACL). 2015. p. 31-39. (2nd Computational Linguistics and Clinical Psychology: From Linguistic Signal to Clinical Reality, CLPsych 2015 - Proceedings of the Workshop).

Coppersmith, Glen ; Dredze, Mark ; Harman, Craig et al. / CLPsych 2015 Shared Task : Depression and PTSD on Twitter. 2nd Computational Linguistics and Clinical Psychology: From Linguistic Signal to Clinical Reality, CLPsych 2015 - Proceedings of the Workshop. Association for Computational Linguistics (ACL), 2015. pp. 31-39 (2nd Computational Linguistics and Clinical Psychology: From Linguistic Signal to Clinical Reality, CLPsych 2015 - Proceedings of the Workshop).

@inproceedings{26955ce4f86a4502b145d5bec8ca37e1,

title = "CLPsych 2015 Shared Task: Depression and PTSD on Twitter",

abstract = "This paper presents a summary of the Computational Linguistics and Clinical Psychology (CLPsych) 2015 shared and unshared tasks. These tasks aimed to provide apples-to-apples comparisons of various approaches to modeling language relevant to mental health from social media. The data used for these tasks is from Twitter users who state a diagnosis of depression or post traumatic stress disorder (PTSD) and demographically-matched community controls. The unshared task was a hackathon held at Johns Hopkins University in November 2014 to explore the data, and the shared task was conducted remotely, with each participating team submitted scores for a held-back test set of users. The shared task consisted of three binary classification experiments: (1) depression versus control, (2) PTSD versus control, and (3) depression versus PTSD. Classifiers were compared primarily via their average precision, though a number of other metrics are used along with this to allow a more nuanced interpretation of the performance measures.",

author = "Glen Coppersmith and Mark Dredze and Craig Harman and Kristy Hollingshead and Margaret Mitchell",

note = "Publisher Copyright: {\textcopyright} 2015 Association for Computational Linguistics; 2nd Workshop on Computational Linguistics and Clinical Psychology: From Linguistic Signal to Clinical Reality, CLPsych 2015 ; Conference date: 05-06-2015",

year = "2015",

language = "English (US)",

series = "2nd Computational Linguistics and Clinical Psychology: From Linguistic Signal to Clinical Reality, CLPsych 2015 - Proceedings of the Workshop",

publisher = "Association for Computational Linguistics (ACL)",

pages = "31--39",

booktitle = "2nd Computational Linguistics and Clinical Psychology",

address = "United States",

}

TY - GEN

T1 - CLPsych 2015 Shared Task

T2 - 2nd Workshop on Computational Linguistics and Clinical Psychology: From Linguistic Signal to Clinical Reality, CLPsych 2015

AU - Coppersmith, Glen

AU - Dredze, Mark

AU - Harman, Craig

AU - Hollingshead, Kristy

AU - Mitchell, Margaret

PY - 2015

Y1 - 2015

N2 - This paper presents a summary of the Computational Linguistics and Clinical Psychology (CLPsych) 2015 shared and unshared tasks. These tasks aimed to provide apples-to-apples comparisons of various approaches to modeling language relevant to mental health from social media. The data used for these tasks is from Twitter users who state a diagnosis of depression or post traumatic stress disorder (PTSD) and demographically-matched community controls. The unshared task was a hackathon held at Johns Hopkins University in November 2014 to explore the data, and the shared task was conducted remotely, with each participating team submitted scores for a held-back test set of users. The shared task consisted of three binary classification experiments: (1) depression versus control, (2) PTSD versus control, and (3) depression versus PTSD. Classifiers were compared primarily via their average precision, though a number of other metrics are used along with this to allow a more nuanced interpretation of the performance measures.

AB - This paper presents a summary of the Computational Linguistics and Clinical Psychology (CLPsych) 2015 shared and unshared tasks. These tasks aimed to provide apples-to-apples comparisons of various approaches to modeling language relevant to mental health from social media. The data used for these tasks is from Twitter users who state a diagnosis of depression or post traumatic stress disorder (PTSD) and demographically-matched community controls. The unshared task was a hackathon held at Johns Hopkins University in November 2014 to explore the data, and the shared task was conducted remotely, with each participating team submitted scores for a held-back test set of users. The shared task consisted of three binary classification experiments: (1) depression versus control, (2) PTSD versus control, and (3) depression versus PTSD. Classifiers were compared primarily via their average precision, though a number of other metrics are used along with this to allow a more nuanced interpretation of the performance measures.

UR - http://www.scopus.com/inward/record.url?scp=85110674457&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85110674457&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:85110674457

T3 - 2nd Computational Linguistics and Clinical Psychology: From Linguistic Signal to Clinical Reality, CLPsych 2015 - Proceedings of the Workshop

SP - 31

EP - 39

BT - 2nd Computational Linguistics and Clinical Psychology

PB - Association for Computational Linguistics (ACL)

Y2 - 5 June 2015

ER -

CLPsych 2015 Shared Task: Depression and PTSD on Twitter

Abstract

Publication series

Conference

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this