Fairness sex

94.4% passed tests (34 passed / 2 failed).

Precision Per Class Female

Precision female - Precision combined.

Threshold: 0.075

Data	anger	happiness	neutral	sadness
iemocap-2.3.0-full	-0.02	0.02	0.09	0.01
msppodcast-2.6.0-emotion.categories.test-1.gold_standard	-0.01	-0.04	0.04	-0.03
mean	-0.01	-0.01	0.07	-0.01

Precision Per Class Male

Precision male - Precision combined.

Threshold: 0.075

Data	anger	happiness	neutral	sadness
iemocap-2.3.0-full	0.02	-0.02	-0.09	-0.01
msppodcast-2.6.0-emotion.categories.test-1.gold_standard	0.01	0.05	-0.03	0.03
mean	0.01	0.02	-0.06	0.01

Recall Per Class Female

Recall female - Recall combined.

Threshold: 0.175

Data	anger	happiness	neutral	sadness
iemocap-2.3.0-full	0.03	0.05	0.01	0.00
msppodcast-2.6.0-emotion.categories.test-1.gold_standard	-0.03	0.04	-0.06	-0.10
mean	0.00	0.04	-0.02	-0.05

Recall Per Class Male

Recall female - Recall combined.

Threshold: 0.175

Data	anger	happiness	neutral	sadness
iemocap-2.3.0-full	-0.03	-0.05	-0.01	-0.00
msppodcast-2.6.0-emotion.categories.test-1.gold_standard	0.03	-0.04	0.06	0.10
mean	0.00	-0.04	0.02	0.05

Unweighted Average Recall Female

UAR Female - UAR combined.

Threshold: 0.075

Data	Unweighted Average Recall Female
iemocap-2.3.0-full	0.02
msppodcast-2.6.0-emotion.categories.test-1.gold_standard	-0.04
mean	-0.01

Unweighted Average Recall Male

UAR Male - UAR combined.

Threshold: 0.075

Data	Unweighted Average Recall Male
iemocap-2.3.0-full	-0.02
msppodcast-2.6.0-emotion.categories.test-1.gold_standard	0.04
mean	0.01

Visualization