AFL-BERT : Enhancing Minority Class Detection in Multi-Label Text Classification with Adaptive Focal Loss and BERT

Fine-tuning transformer models like Bidirectional Encoder Representations from Transformers has enhanced text classification performance. However, class imbalance remains a challenge, causing biased predictions. This study introduces an improved training strategy using a novel Adaptive Focal Loss with dynamically adjusted γ based on class frequencies. Unlike static γ values, this method emphasizes minority classes automatically. Experiments on the CMU Movie Summary dataset show Adaptive Focal Loss surpasses standard binary cross-entropy and Focal Loss, achieving an F1-score of 0.5, ROC accuracy of 0.79, and Micro Recall of 0.53. These results demonstrate the effectiveness of adaptive focusing methods in improving the detection of minority classes in imbalanced scenarios.

@article{Labd2025,
  title     = {AFL-BERT : Enhancing Minority Class Detection in Multi-Label Text Classification with Adaptive Focal Loss and BERT},
  journal   = {International Journal of Advanced Computer Science and Applications},
  volume    = {16},
  number    = {7},
  year      = {2025},
  publisher = {The Science and Information Organization},
  author    = {Zakia Labd and Said Bahassine and Khalid Housni},
  doi       = {10.14569/IJACSA.2025.0160749},
  url       = {https://doi.org/10.14569/IJACSA.2025.0160749}
}