Table 5.

F-measure based on cross-domain experiments for Task 1

Test set	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	53.56	42.58	57.88	57.54	58.43	58.90	59.93	58.26	60.20	58.46
	RF	54.55	44.74	56.68	55.32	57.20	62.64	60.08	61.35	63.73	63.00
	SVM	51.42	44.20	57.14	47.49	49.47	60.45	61.56	61.09	61.30	63.32
TDF	MC	27.36	27.36	27.36	27.36	27.36	27.36	27.36	27.36	27.36	27.36
	LR	44.01	28.81	44.45	50.41	51.96	56.11	59.81	54.14	57.28	56.17
	RF	34.20	31.37	47.40	50.40	53.02	50.86	49.16	43.85	54.76	46.34
	SVM	40.68	31.30	47.38	36.57	38.06	59.03	56.42	59.51	59.51	61.02
GRGE	MC	44.63	44.63	44.63	44.63	44.63	44.63	44.63	44.63	44.63	44.63
	LR	51.14	45.79	49.20	56.63	56.49	60.06	55.90	56.43	61.32	59.22
	RF	46.17	46.62	49.85	58.03	58.97	48.27	52.84	48.46	51.27	48.13
	SVM	53.56	46.38	51.61	45.68	47.31	63.71	62.01	63.19	57.07	63.04
avg	MC	37.71	37.71	37.71	37.71	37.71	37.71	37.71	37.71	37.71	37.71
	LR	49.57	39.06	50.51	54.86	55.63	58.36	58.55	56.28	59.60	57.95
	RF	44.97	40.91	51.31	54.58	56.40	53.92	54.03	51.22	56.59	52.49
	SVM	48.55	40.63	52.04	43.25	44.95	61.06	60.00	61.26	59.29	62.46
relative decrease (%)	LR	27.23	14.68	9.48	9.90	9.53	11.05	16.29	15.74	11.35	14.69
	RF	30.86	14.49	12.22	10.13	11.83	19.26	18.46	22.95	16.68	22.21
	SVM	26.78	14.68	4.46	23.79	21.57	11.03	12.29	10.56	14.97	11.03

The first column indicates the test dataset, after training the models on the rest

The best performing feature set per algorithm is highlighted in bold