. 2020 Apr 1;6(2):e14952. doi: 10.2196/14952

Table 8.

Classifier results for each category (N=50).

Source and category		Random forest		Support vector machine		Convolutional neural network
		Accuracy, n (%)	Balanced accuracy	Accuracy, n (%)	Balanced accuracy	Accuracy, n (%)	Balanced accuracy
WebMD
	Share experiences^a	41 (82)	0.83^b	41 (82)	0.81	41 (82)	0.82
	Ask for specific medical advice or information^a	40 (80)	0.82	41 (82)	0.83^b	37 (74)	0.76
	Request or give psychological support^a	39 (78)	0.71	43 (86)	0.8 ^b	38 (76)	0.68
	About Family (Not about self)^a	38 (76)	0.56	40 (80)	0.89^b	47 (94)	0.81
DailyStrength
	Share experiences^a	41 (82)	0.80	40 (80)	0.70	41 (82)	0.82^b
	Ask for specific medical advice or information^a	39 (78)	0.71	38 (76)	0.70	37 (74)	0.7 ^b
	Request or give psychological support	34 (68)	0.68	33 (66)	0.65	38 (76)	0.68^b
TwitterHealth
	Share experiences^a	39 (78)	0.77	41 (82)	0.82^b	43 (86)	0.74
	Share news^a	41 (82)	0.64	40 (80)	0.73	47 (94)	0.81
Google+Health
	Share experiences	44 (88)	0.48	35 (70)	0.72^b	45 (90)	0.60
	Share news	26 (52)	0.48	28 (56)	0.52	33 (66)	0.59^b
	Advertisement	38 (76)	0.59	24 (48)	0.53	42 (84)	0.6 ^b
	Personal opinion	39 (78)	0.48	37 (74)	0.71^b	42 (84)	0.60
	Educational material^a	40 (80)	0.66	34 (68)	0.76	41 (82)	0.79^b

^aThe category of each source-category combination with at least one classifier that achieved a balanced accuracy of at least 0.75.

^bThe highest balanced accuracy for each source-category combination.