Table 2.

Performance of the machine learning models.

Model performance and feature set		SVMa, mean (SD)	DTb, mean (SD)	RFc, mean (SD)	LRd, mean (SD)
Precision
	Ae	.88 (.01)	.84 (.02)	.87 (.01)	.87 (.01)
	Bf	.88 (.01)	.76 (.01)	.85 (.01)	.87 (.01)
	Cg	.85 (.01)	.76 (.01)	.85 (.01)	.88 (.01)
Recall
	A	.78 (.02)	.68 (.05)	.75 (.02)	.79 (.02)
	B	.80 (.01)	.75 (.01)	.74 (.01)	.79 (.01)
	C	.85 (.01)	.75 (.01)	.73 (.01)	.80 (.01)
F-measure
	A	.83 (.01)	.74 (.03)	.80 (.01)	.83 (.01)
	B	.84 (.01)	.76 (.01)	.79 (.01)	.83 (.01)
	C	.85 (.01)	.76 (.01)	.78 (.01)	.84 (.01)
Accuracy
	A	.85 (.01)	.79 (.02)	.83 (.01)	.85 (.01)
	B	.86 (.01)	.78 (.01)	.82 (.01)	.85 (.01)
	C	.86 (.01)	.78 (.01)	.82 (.01)	.86 (.01)

^aSVM: support vector machine.

^bDT: decision tree.

^cRF: random forest.

^dLR: logistic regression.

^eA: n-gram features.

^fB: n-gram features + domain knowledge features.

^gC: n-gram features + domain knowledge features + theory-motivated features.