Table 7.

Detection model performance with the depression-domain lexicon.

Detection model	Precision	Recall	F1	Accuracy
NBa	67%	67%	67%	67%
Lb-NB	74%	73%	73%	73%
LRc	76%	76%	75%	76%
L-LR	77%	77%	77%	77%
RFd	68%	68%	68%	68%
L-RF	77%	77%	76%	77%
SVMe	65%	65%	65%	65%
L-SVM	74%	72%	72%	72%
DTf	67%	67%	67%	67%
L-DT	69%	69%	69%	69%

^aNB: naive Bayes.

^bL: depression-domain lexicon as a feature.

^cLR: logistic regression.

^dRF: random forest.

^eSVM: support vector machine.

^fDT: decision tree.