On estimating depressive tendencies of Twitter users utilizing their tweet data

Sho Tsugawa; Yukiko Mogi; Yusuke Kikuchi; Fumio Kishino; Kazuyuki Fujita; Yuichi Itoh; Hiroyuki Ohsaki

doi:10.1109/VR.2013.6549431

On estimating depressive tendencies of Twitter users utilizing their tweet data

Sho Tsugawa, Yukiko Mogi, Yusuke Kikuchi, Fumio Kishino, Kazuyuki Fujita, Yuichi Itoh, Hiroyuki Ohsaki

RIEC - Human and Bio Information Systems Division

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

21 Citations (Scopus)

Abstract

In this paper, we investigate the effectiveness of the records of user's activities in Twitter, which is a popular microblogging site, for estimating his/her depressive tendency. We construct multiple regression model to estimate user's depressive tendency from the frequencies of words used by the user. We perform experiments to estimate participants' depressive tendencies using the constructed regression model. Our experimental results show that there exists medium positive correlation (correlation coefficient r ≃ 0.45) between the Zung's Self-rating Depression Scale, which is a popular measure for estimating depressive tendency, and estimated score obtained from the regression model.

Original language	English
Title of host publication	IEEE Virtual Reality Conference 2013, VR 2013 - Proceedings
DOIs	https://doi.org/10.1109/VR.2013.6549431
Publication status	Published - 2013
Event	20th IEEE Virtual Reality Conference, VR 2013 - Orlando, FL, United States Duration: 2013 Mar 16 → 2013 Mar 20

Publication series

Name	Proceedings - IEEE Virtual Reality

Conference

Conference	20th IEEE Virtual Reality Conference, VR 2013
Country/Territory	United States
City	Orlando, FL
Period	13/3/16 → 13/3/20

Keywords

Depression
Multiple Regression Analysis
Twitter
Zung's Self-rating Depression Scale

Access to Document

10.1109/VR.2013.6549431

Cite this

@inproceedings{4de644a664be4f78a4d9c086cae7026d,

title = "On estimating depressive tendencies of Twitter users utilizing their tweet data",

abstract = "In this paper, we investigate the effectiveness of the records of user's activities in Twitter, which is a popular microblogging site, for estimating his/her depressive tendency. We construct multiple regression model to estimate user's depressive tendency from the frequencies of words used by the user. We perform experiments to estimate participants' depressive tendencies using the constructed regression model. Our experimental results show that there exists medium positive correlation (correlation coefficient r ≃ 0.45) between the Zung's Self-rating Depression Scale, which is a popular measure for estimating depressive tendency, and estimated score obtained from the regression model.",

keywords = "Depression, Multiple Regression Analysis, Twitter, Zung's Self-rating Depression Scale",

author = "Sho Tsugawa and Yukiko Mogi and Yusuke Kikuchi and Fumio Kishino and Kazuyuki Fujita and Yuichi Itoh and Hiroyuki Ohsaki",

year = "2013",

doi = "10.1109/VR.2013.6549431",

language = "English",

isbn = "9781467347952",

series = "Proceedings - IEEE Virtual Reality",

booktitle = "IEEE Virtual Reality Conference 2013, VR 2013 - Proceedings",

note = "20th IEEE Virtual Reality Conference, VR 2013 ; Conference date: 16-03-2013 Through 20-03-2013",

}

Tsugawa, S, Mogi, Y, Kikuchi, Y, Kishino, F, Fujita, K, Itoh, Y & Ohsaki, H 2013, On estimating depressive tendencies of Twitter users utilizing their tweet data. in IEEE Virtual Reality Conference 2013, VR 2013 - Proceedings., 6549431, Proceedings - IEEE Virtual Reality, 20th IEEE Virtual Reality Conference, VR 2013, Orlando, FL, United States, 13/3/16. https://doi.org/10.1109/VR.2013.6549431

TY - GEN

T1 - On estimating depressive tendencies of Twitter users utilizing their tweet data

AU - Tsugawa, Sho

AU - Mogi, Yukiko

AU - Kikuchi, Yusuke

AU - Kishino, Fumio

AU - Fujita, Kazuyuki

AU - Itoh, Yuichi

AU - Ohsaki, Hiroyuki

PY - 2013

Y1 - 2013

N2 - In this paper, we investigate the effectiveness of the records of user's activities in Twitter, which is a popular microblogging site, for estimating his/her depressive tendency. We construct multiple regression model to estimate user's depressive tendency from the frequencies of words used by the user. We perform experiments to estimate participants' depressive tendencies using the constructed regression model. Our experimental results show that there exists medium positive correlation (correlation coefficient r ≃ 0.45) between the Zung's Self-rating Depression Scale, which is a popular measure for estimating depressive tendency, and estimated score obtained from the regression model.

AB - In this paper, we investigate the effectiveness of the records of user's activities in Twitter, which is a popular microblogging site, for estimating his/her depressive tendency. We construct multiple regression model to estimate user's depressive tendency from the frequencies of words used by the user. We perform experiments to estimate participants' depressive tendencies using the constructed regression model. Our experimental results show that there exists medium positive correlation (correlation coefficient r ≃ 0.45) between the Zung's Self-rating Depression Scale, which is a popular measure for estimating depressive tendency, and estimated score obtained from the regression model.

KW - Depression

KW - Multiple Regression Analysis

KW - Twitter

KW - Zung's Self-rating Depression Scale

UR - http://www.scopus.com/inward/record.url?scp=84884835655&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84884835655&partnerID=8YFLogxK

U2 - 10.1109/VR.2013.6549431

DO - 10.1109/VR.2013.6549431

M3 - Conference contribution

AN - SCOPUS:84884835655

SN - 9781467347952

T3 - Proceedings - IEEE Virtual Reality

BT - IEEE Virtual Reality Conference 2013, VR 2013 - Proceedings

T2 - 20th IEEE Virtual Reality Conference, VR 2013

Y2 - 16 March 2013 through 20 March 2013

ER -

On estimating depressive tendencies of Twitter users utilizing their tweet data

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this