Predicting depression from language-based emotion dynamics: Longitudinal analysis of facebook and twitter status updates

Elizabeth M. Seabrook, Margaret L. Kern, Ben D. Fulcher, Nikki S. Rickard

Research output: Contribution to journalArticleResearchpeer-review

Abstract

Background: Frequent expression of negative emotion words on social media has been linked to depression. However, metrics have relied on average values, not dynamic measures of emotional volatility. Objective: The aim of this study was to report on the associations between depression severity and the variability (time-unstructured) and instability (time-structured) in emotion word expression on Facebook and Twitter across status updates. Methods: Status updates and depression severity ratings of 29 Facebook users and 49 Twitter users were collected through the app MoodPrism. The average proportion of positive and negative emotion words used, within-person variability, and instability were computed. Results: Negative emotion word instability was a significant predictor of greater depression severity on Facebook (rs(29)=.44, P=.02, 95% CI 0.09-0.69), even after controlling for the average proportion of negative emotion words used (partial rs(26)=.51, P=.006) and within-person variability (partial rs(26)=.49, P=.009). A different pattern emerged on Twitter where greater negative emotion word variability indicated lower depression severity (rs(49)=−.34, P=.01, 95% CI −0.58 to 0.09). Differences between Facebook and Twitter users in their emotion word patterns and psychological characteristics were also explored. Conclusions: The findings suggest that negative emotion word instability may be a simple yet sensitive measure of time-structured variability, useful when screening for depression through social media, though its usefulness may depend on the social media platform.

Original languageEnglish
Article numbere168
Number of pages17
JournalJournal of Medical Internet Research
Volume20
Issue number5
DOIs
Publication statusPublished - 1 May 2018

Keywords

  • Automated text analysis
  • Depression
  • Emotions
  • Facebook
  • Instability
  • Twitter
  • Variability

Cite this

@article{3280fb13bc2b456d9dff71e8dca605a0,
title = "Predicting depression from language-based emotion dynamics: Longitudinal analysis of facebook and twitter status updates",
abstract = "Background: Frequent expression of negative emotion words on social media has been linked to depression. However, metrics have relied on average values, not dynamic measures of emotional volatility. Objective: The aim of this study was to report on the associations between depression severity and the variability (time-unstructured) and instability (time-structured) in emotion word expression on Facebook and Twitter across status updates. Methods: Status updates and depression severity ratings of 29 Facebook users and 49 Twitter users were collected through the app MoodPrism. The average proportion of positive and negative emotion words used, within-person variability, and instability were computed. Results: Negative emotion word instability was a significant predictor of greater depression severity on Facebook (rs(29)=.44, P=.02, 95{\%} CI 0.09-0.69), even after controlling for the average proportion of negative emotion words used (partial rs(26)=.51, P=.006) and within-person variability (partial rs(26)=.49, P=.009). A different pattern emerged on Twitter where greater negative emotion word variability indicated lower depression severity (rs(49)=−.34, P=.01, 95{\%} CI −0.58 to 0.09). Differences between Facebook and Twitter users in their emotion word patterns and psychological characteristics were also explored. Conclusions: The findings suggest that negative emotion word instability may be a simple yet sensitive measure of time-structured variability, useful when screening for depression through social media, though its usefulness may depend on the social media platform.",
keywords = "Automated text analysis, Depression, Emotions, Facebook, Instability, Twitter, Variability",
author = "Seabrook, {Elizabeth M.} and Kern, {Margaret L.} and Fulcher, {Ben D.} and Rickard, {Nikki S.}",
year = "2018",
month = "5",
day = "1",
doi = "10.2196/jmir.9267",
language = "English",
volume = "20",
journal = "Journal of Medical Internet Research",
issn = "1439-4456",
publisher = "Journal of Medical Internet Research",
number = "5",

}

Predicting depression from language-based emotion dynamics : Longitudinal analysis of facebook and twitter status updates. / Seabrook, Elizabeth M.; Kern, Margaret L.; Fulcher, Ben D.; Rickard, Nikki S.

In: Journal of Medical Internet Research, Vol. 20, No. 5, e168, 01.05.2018.

Research output: Contribution to journalArticleResearchpeer-review

TY - JOUR

T1 - Predicting depression from language-based emotion dynamics

T2 - Longitudinal analysis of facebook and twitter status updates

AU - Seabrook, Elizabeth M.

AU - Kern, Margaret L.

AU - Fulcher, Ben D.

AU - Rickard, Nikki S.

PY - 2018/5/1

Y1 - 2018/5/1

N2 - Background: Frequent expression of negative emotion words on social media has been linked to depression. However, metrics have relied on average values, not dynamic measures of emotional volatility. Objective: The aim of this study was to report on the associations between depression severity and the variability (time-unstructured) and instability (time-structured) in emotion word expression on Facebook and Twitter across status updates. Methods: Status updates and depression severity ratings of 29 Facebook users and 49 Twitter users were collected through the app MoodPrism. The average proportion of positive and negative emotion words used, within-person variability, and instability were computed. Results: Negative emotion word instability was a significant predictor of greater depression severity on Facebook (rs(29)=.44, P=.02, 95% CI 0.09-0.69), even after controlling for the average proportion of negative emotion words used (partial rs(26)=.51, P=.006) and within-person variability (partial rs(26)=.49, P=.009). A different pattern emerged on Twitter where greater negative emotion word variability indicated lower depression severity (rs(49)=−.34, P=.01, 95% CI −0.58 to 0.09). Differences between Facebook and Twitter users in their emotion word patterns and psychological characteristics were also explored. Conclusions: The findings suggest that negative emotion word instability may be a simple yet sensitive measure of time-structured variability, useful when screening for depression through social media, though its usefulness may depend on the social media platform.

AB - Background: Frequent expression of negative emotion words on social media has been linked to depression. However, metrics have relied on average values, not dynamic measures of emotional volatility. Objective: The aim of this study was to report on the associations between depression severity and the variability (time-unstructured) and instability (time-structured) in emotion word expression on Facebook and Twitter across status updates. Methods: Status updates and depression severity ratings of 29 Facebook users and 49 Twitter users were collected through the app MoodPrism. The average proportion of positive and negative emotion words used, within-person variability, and instability were computed. Results: Negative emotion word instability was a significant predictor of greater depression severity on Facebook (rs(29)=.44, P=.02, 95% CI 0.09-0.69), even after controlling for the average proportion of negative emotion words used (partial rs(26)=.51, P=.006) and within-person variability (partial rs(26)=.49, P=.009). A different pattern emerged on Twitter where greater negative emotion word variability indicated lower depression severity (rs(49)=−.34, P=.01, 95% CI −0.58 to 0.09). Differences between Facebook and Twitter users in their emotion word patterns and psychological characteristics were also explored. Conclusions: The findings suggest that negative emotion word instability may be a simple yet sensitive measure of time-structured variability, useful when screening for depression through social media, though its usefulness may depend on the social media platform.

KW - Automated text analysis

KW - Depression

KW - Emotions

KW - Facebook

KW - Instability

KW - Twitter

KW - Variability

UR - http://www.scopus.com/inward/record.url?scp=85047569467&partnerID=8YFLogxK

U2 - 10.2196/jmir.9267

DO - 10.2196/jmir.9267

M3 - Article

VL - 20

JO - Journal of Medical Internet Research

JF - Journal of Medical Internet Research

SN - 1439-4456

IS - 5

M1 - e168

ER -