Table 7.

Pearson correlation for the emotion prediction task (Task 2), using 5-fold cross validation

Emotion	Algorithm	Baselines		Our resources				Combinations
		N	L${}_{\mathit{tr}}$	L${}_g$	L${}_{\mathit{tw}}$	L	E	NL	NE	LE	NLE
Fear	MC${}_{\mathit{avg}}$	.000	.000	.000	.000	.000	.000	.000	.000	.000	.000
	MC${}_{\mathit{dist}}$	.000	.000	.000	.000	.000	.000	.000	.000	.000	.000
	LASSO	.200	-.020	.043	.119	.092	.148	.213	.243	.162	.226
	RFR	.192	.007	.086	.214	.203	.188	.266	.222	.192	.225
	SVR	.197	.022	.146	.210	.196	.276	.135	.239	.278	.240
	Average	.196	.003	.092	.181	.164	.204	.205	.235	.211	.230
Happy	MC${}_{\mathit{avg}}$	.000	.000	.000	.000	.000	.000	.000	.000	.000	.000
	MC${}_{\mathit{dist}}$	.000	.000	.000	.000	.000	.000	.000	.000	.000	.000
	LASSO	.345	.099	.276	.283	.324	.353	.341	.360	.353	.364
	RFR	.370	.162	.343	.429	.446	.499	.458	.498	.502	.501
	SVR	.388	.158	.287	.471	.462	.501	.409	.468	.495	.463
	Average	.368	.140	.302	.394	.411	.451	.403	.442	.450	.443
Sad	MC${}_{\mathit{avg}}$	.000	.000	.000	.000	.000	.000	.000	.000	.000	.000
	MC${}_{\mathit{dist}}$	.000	.000	.000	.000	.000	.000	.000	.000	.000	.000
	LASSO	.311	.071	.184	.218	.213	.267	.322	.355	.263	.361
	RFR	.357	.061	.226	.346	.376	.452	.400	.453	.453	.453
	SVR	.358	.094	.161	.346	.327	.443	.249	.409	.428	.395
	Average	.342	.075	.190	.303	.305	.387	.324	.406	.381	.403
Surprise	MC${}_{\mathit{avg}}$	.000	.000	.000	.000	.000	.000	.000	.000	.000	.000
	MC${}_{\mathit{dist}}$	.000	.000	.000	.000	.000	.000	.000	.000	.000	.000
	LASSO	.265	.067	.084	.277	.258	.259	.272	.376	.269	.385
	RFR	.417	.073	.226	.442	.465	.513	.480	.519	.517	.521
	SVR	.370	.031	.143	.399	.388	.449	.364	.415	.482	.451
	Average	.351	.057	.151	.373	.370	.407	.372	.437	.423	.452

The best performing feature set per algorithm is highlighted in bold