sag-uniroma2/INFVague_MODEL

Task Title

Informative vs Non-Informative/Vague Text Identification (INFVague)

Task Description

Binary classification model for identifying whether sustainability disclosures are informative or vague/non-informative.

Dataset Summary

• Total samples: 732
• Informative: 629
• Non-Informative/Vague: 103

Model

• Base model: bert-base-cased

Performance

• Accuracy: 87.2% ± 2.1
• Macro F1: 67.5% ± 8.9

Results are reported as Mean ± SD across 10-fold cross-validation, where each fold was used once as the test set.