Evaluation

Detailed evaluation criteria for MiSonGyny

The evaluation of the MiSonGyny task will focus on two main subtasks, each with its own specific criteria. For both subtasks, the macro-F1 score will be used as the primary evaluation metric.

What metrics will be reported?

• Precision: To provide a clear view of the model's ability to avoid false positives.

• Recall: To evaluate the model's ability to find all actual positive cases.

• Macro-F1 score: The average of the individual F1-scores for each class or category.