Skip to main content

Table 5 Algorithm maximum precision and validation scores according to account and tweet models

From: Hate is in the air! But where? Introducing an algorithm to detect hate speech in digital microenvironments

Model

Precision

Recall

F1-score

Fivefold

Account

 Neutral

0.99

0.65

0.79

 

 Hate speech

0.03

0.62

0.05

 

 Average/total

0.98

0.65

0.78

0.63

Tweet

 Neutral

1.00

0.87

0.93

 

 Hate speech

0.09

0.86

0.17

 

 Average/total

0.98

0.87

0.92

0.86

  1. Parameters: number of estimators = 1000; maximum depth = 10