Task Title

High Potential Blue and Greenwashing Detection (HPGW) as Weak-Disclosure Risk Proxy

Task Description

Binary classification model for identifying high potential blue/greenwashing as weak-disclosure risk proxies based on disclosure quality characteristics. High potential cases are defined as non-informative and qualitative disclosures, whereas low potential cases are defined as informative and quantitative disclosures.

Dataset Summary

  • Total samples: 542
  • High Potential BGW: 457
  • Low Potential BGW: 85

Model

  • Base model: bert-base-cased

Performance

  • Accuracy: 91.0% ± 3.5
  • Macro F1: 79.3% ± 12.3

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

Downloads last month
67
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for sag-uniroma2/HPGW_MODEL

Finetuned
(2908)
this model

Collection including sag-uniroma2/HPGW_MODEL