Table 4.

F-measure based on 10-fold cross-validation for Task 1

Dataset	Model	Baselines		Our resources				Combinations
		N	L${}_{\mathit{tr}}$	L${}_g$	L${}_{\mathit{tw}}$	L	E	NL	NE	LE	NLE
TIFF	MC	41.15	41.15	41.15	41.15	41.15	41.15	41.15	41.15	41.15	41.15
	LR	61.35	42.75	55.32	56.29	57.83	59.56	63.29	60.28	62.28	62.49
	RF	56.93	44.20	57.99	56.08	59.54	59.79	59.90	59.00	61.51	60.62
	SVM	59.52	43.99	58.00	48.31	49.73	61.96	62.11	62.53	63.58	64.34
TDF	MC	27.36	27.36	27.36	27.36	27.36	27.36	27.36	27.36	27.36	27.36
	LR	62.64	42.48	51.22	53.87	54.17	60.56	65.87	62.27	61.86	63.23
	RF	58.85	45.96	52.05	54.67	59.18	62.40	62.45	62.42	63.97	63.85
	SVM	60.24	46.05	51.64	53.65	53.75	63.29	63.75	63.22	65.28	66.53
GRGE	MC	44.63	44.63	44.63	44.63	44.63	44.63	44.63	44.63	44.63	44.63
	LR	80.37	52.11	60.86	72.52	72.46	76.72	80.66	77.82	77.55	78.06
	RF	79.35	53.35	65.32	71.43	73.19	78.14	76.42	78.01	78.28	77.98
	SVM	79.17	52.82	62.76	68.30	68.44	80.65	79.36	79.71	80.32	79.72
avg	MC	37.71	37.71	37.71	37.71	37.71	37.71	37.71	37.71	37.71	37.71
	LR	68.12	45.78	55.80	60.89	61.49	65.61	69.94	66.79	67.23	67.93
	RF	65.04	47.84	58.45	60.73	63.97	66.78	66.26	66.48	67.92	67.48
	SVM	66.31	47.62	54.47	56.75	57.31	68.63	68.41	68.49	69.73	70.20

The best performing feature set per algorithm is highlighted in bold