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

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 (r_s(29)=.44, P=.02, 95% CI 0.09-0.69), even after controlling for the average proportion of negative emotion words used (partial r_s(26)=.51, P=.006) and within-person variability (partial r_s(26)=.49, P=.009). A different pattern emerged on Twitter where greater negative emotion word variability indicated lower depression severity (r_s(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.