Why Do They Leave: Modeling Participation in Online Depression Forums

Farig Sadeque; Ted Pedersen; Thamar Solorio; Prasha Shrestha; Nicolas Rey-Villamizar; Steven Bethard

Why Do They Leave: Modeling Participation in Online Depression Forums

Farig Sadeque, Ted Pedersen, Thamar Solorio, Prasha Shrestha, Nicolas Rey-Villamizar, Steven Bethard

Computer Science (Duluth)

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

14 Scopus citations

Abstract

Depression is a major threat to public health, accounting for almost 12% of all disabilities and claiming the life of 1 out of 5 patients suffering from it. Since depression is often signaled by decreasing social interaction, we explored how analysis of online health forums may help identify such episodes. We collected posts and replies from users of several forums on healthboards.com and analyzed changes in their use of language and activity levels over time. We found that users in the Depression forum use fewer social words, and have some revealing phrases associated with their last posts (e.g., cut myself). Our models based on these findings achieved 94 F₁ for detecting users who will withdraw from a Depression forum by the end of a 1-year observation period.

Original language	English (US)
Title of host publication	EMNLP 2016 - Conference on Empirical Methods in Natural Language Processing, Proceedings of the 4th International Workshop on Natural Language Processing for Social Media, SocialNLP 2016
Publisher	Association for Computational Linguistics (ACL)
Pages	14-19
Number of pages	6
ISBN (Electronic)	9781945626326
State	Published - 2016
Event	4th ACM Workshop on Natural Language Processing for Social Media, SocialNLP 2016, associated with the Conference on Empirical Methods in Natural Language Processing, EMNLP 2016 - Austin, United States Duration: Nov 1 2016 → Nov 1 2016

Publication series

Name	EMNLP 2016 - Conference on Empirical Methods in Natural Language Processing, Proceedings of the 4th International Workshop on Natural Language Processing for Social Media, SocialNLP 2016

Conference

Conference	4th ACM Workshop on Natural Language Processing for Social Media, SocialNLP 2016, associated with the Conference on Empirical Methods in Natural Language Processing, EMNLP 2016
Country/Territory	United States
City	Austin
Period	11/1/16 → 11/1/16

Bibliographical note

Publisher Copyright:
© 2016 Association for Computational Linguistics

OpenUrl availability

Full text

Cite this

Sadeque, F., Pedersen, T., Solorio, T., Shrestha, P., Rey-Villamizar, N., & Bethard, S. (2016). Why Do They Leave: Modeling Participation in Online Depression Forums. In EMNLP 2016 - Conference on Empirical Methods in Natural Language Processing, Proceedings of the 4th International Workshop on Natural Language Processing for Social Media, SocialNLP 2016 (pp. 14-19). (EMNLP 2016 - Conference on Empirical Methods in Natural Language Processing, Proceedings of the 4th International Workshop on Natural Language Processing for Social Media, SocialNLP 2016). Association for Computational Linguistics (ACL).

Why Do They Leave: Modeling Participation in Online Depression Forums. / Sadeque, Farig; Pedersen, Ted; Solorio, Thamar et al.
EMNLP 2016 - Conference on Empirical Methods in Natural Language Processing, Proceedings of the 4th International Workshop on Natural Language Processing for Social Media, SocialNLP 2016. Association for Computational Linguistics (ACL), 2016. p. 14-19 (EMNLP 2016 - Conference on Empirical Methods in Natural Language Processing, Proceedings of the 4th International Workshop on Natural Language Processing for Social Media, SocialNLP 2016).

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

Sadeque, F, Pedersen, T, Solorio, T, Shrestha, P, Rey-Villamizar, N & Bethard, S 2016, Why Do They Leave: Modeling Participation in Online Depression Forums. in EMNLP 2016 - Conference on Empirical Methods in Natural Language Processing, Proceedings of the 4th International Workshop on Natural Language Processing for Social Media, SocialNLP 2016. EMNLP 2016 - Conference on Empirical Methods in Natural Language Processing, Proceedings of the 4th International Workshop on Natural Language Processing for Social Media, SocialNLP 2016, Association for Computational Linguistics (ACL), pp. 14-19, 4th ACM Workshop on Natural Language Processing for Social Media, SocialNLP 2016, associated with the Conference on Empirical Methods in Natural Language Processing, EMNLP 2016, Austin, United States, 11/1/16.

Sadeque F, Pedersen T, Solorio T, Shrestha P, Rey-Villamizar N, Bethard S. Why Do They Leave: Modeling Participation in Online Depression Forums. In EMNLP 2016 - Conference on Empirical Methods in Natural Language Processing, Proceedings of the 4th International Workshop on Natural Language Processing for Social Media, SocialNLP 2016. Association for Computational Linguistics (ACL). 2016. p. 14-19. (EMNLP 2016 - Conference on Empirical Methods in Natural Language Processing, Proceedings of the 4th International Workshop on Natural Language Processing for Social Media, SocialNLP 2016).

Sadeque, Farig ; Pedersen, Ted ; Solorio, Thamar et al. / Why Do They Leave : Modeling Participation in Online Depression Forums. EMNLP 2016 - Conference on Empirical Methods in Natural Language Processing, Proceedings of the 4th International Workshop on Natural Language Processing for Social Media, SocialNLP 2016. Association for Computational Linguistics (ACL), 2016. pp. 14-19 (EMNLP 2016 - Conference on Empirical Methods in Natural Language Processing, Proceedings of the 4th International Workshop on Natural Language Processing for Social Media, SocialNLP 2016).

@inproceedings{664d8c760fc24c96850a2c39c5876d0d,

title = "Why Do They Leave: Modeling Participation in Online Depression Forums",

abstract = "Depression is a major threat to public health, accounting for almost 12% of all disabilities and claiming the life of 1 out of 5 patients suffering from it. Since depression is often signaled by decreasing social interaction, we explored how analysis of online health forums may help identify such episodes. We collected posts and replies from users of several forums on healthboards.com and analyzed changes in their use of language and activity levels over time. We found that users in the Depression forum use fewer social words, and have some revealing phrases associated with their last posts (e.g., cut myself). Our models based on these findings achieved 94 F1 for detecting users who will withdraw from a Depression forum by the end of a 1-year observation period.",

author = "Farig Sadeque and Ted Pedersen and Thamar Solorio and Prasha Shrestha and Nicolas Rey-Villamizar and Steven Bethard",

note = "Publisher Copyright: {\textcopyright} 2016 Association for Computational Linguistics; 4th ACM Workshop on Natural Language Processing for Social Media, SocialNLP 2016, associated with the Conference on Empirical Methods in Natural Language Processing, EMNLP 2016 ; Conference date: 01-11-2016 Through 01-11-2016",

year = "2016",

language = "English (US)",

series = "EMNLP 2016 - Conference on Empirical Methods in Natural Language Processing, Proceedings of the 4th International Workshop on Natural Language Processing for Social Media, SocialNLP 2016",

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

pages = "14--19",

booktitle = "EMNLP 2016 - Conference on Empirical Methods in Natural Language Processing, Proceedings of the 4th International Workshop on Natural Language Processing for Social Media, SocialNLP 2016",

}

TY - GEN

T1 - Why Do They Leave

T2 - 4th ACM Workshop on Natural Language Processing for Social Media, SocialNLP 2016, associated with the Conference on Empirical Methods in Natural Language Processing, EMNLP 2016

AU - Sadeque, Farig

AU - Pedersen, Ted

AU - Solorio, Thamar

AU - Shrestha, Prasha

AU - Rey-Villamizar, Nicolas

AU - Bethard, Steven

PY - 2016

Y1 - 2016

N2 - Depression is a major threat to public health, accounting for almost 12% of all disabilities and claiming the life of 1 out of 5 patients suffering from it. Since depression is often signaled by decreasing social interaction, we explored how analysis of online health forums may help identify such episodes. We collected posts and replies from users of several forums on healthboards.com and analyzed changes in their use of language and activity levels over time. We found that users in the Depression forum use fewer social words, and have some revealing phrases associated with their last posts (e.g., cut myself). Our models based on these findings achieved 94 F1 for detecting users who will withdraw from a Depression forum by the end of a 1-year observation period.

AB - Depression is a major threat to public health, accounting for almost 12% of all disabilities and claiming the life of 1 out of 5 patients suffering from it. Since depression is often signaled by decreasing social interaction, we explored how analysis of online health forums may help identify such episodes. We collected posts and replies from users of several forums on healthboards.com and analyzed changes in their use of language and activity levels over time. We found that users in the Depression forum use fewer social words, and have some revealing phrases associated with their last posts (e.g., cut myself). Our models based on these findings achieved 94 F1 for detecting users who will withdraw from a Depression forum by the end of a 1-year observation period.

UR - http://www.scopus.com/inward/record.url?scp=85034785373&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85034785373&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:85034785373

T3 - EMNLP 2016 - Conference on Empirical Methods in Natural Language Processing, Proceedings of the 4th International Workshop on Natural Language Processing for Social Media, SocialNLP 2016

SP - 14

EP - 19

BT - EMNLP 2016 - Conference on Empirical Methods in Natural Language Processing, Proceedings of the 4th International Workshop on Natural Language Processing for Social Media, SocialNLP 2016

PB - Association for Computational Linguistics (ACL)

Y2 - 1 November 2016 through 1 November 2016

ER -

Why Do They Leave: Modeling Participation in Online Depression Forums

Abstract

Publication series

Conference

Bibliographical note

OpenUrl availability

Other files and links

Fingerprint

Cite this