Table 3. Correlations between the random forest predicted and self-reported CES-D.

Feature set	r	p value	RMSE
Baseline (1)	-0.02	0.689	9.15
sentiment (3)	0.08	0.381	8.45
self-reported SWL + sentiment (4)	0.28	0.001	7.90
machine-predicted SWL + sentiment (4)	0.25	0.005	7.96

The baseline model uses the median of the self-reported SWL with variation as feature. Significance of the correlation (p value) and root mean squared error (RMSE) is also provided. Numbers within brackets in the ‘feature set’ column are numbers of features in those sets.