Balancing the Scales: Text Augmentation for Addressing Class Imbalance in the PCL Dataset

Identifying Patronizing and Condescending Language (PCL) is an essential critical task in natural languageprocessing (NLP), relevant to content moderation, bias identification, and online discourse evaluation. The existence ofsubstantial class imbalance in PCL dataset is a considerable difficulty for machine learning models, frequently resulting inbiased predictions and inadequate generalization. This study investigates text augmentation methods to address classimbalance and enhance the efficacy of PCL classifiers. The suggested method analyses news stories from different nationsand determines whether or not they use patronizing or condescending language and categorizes the detected PCL intovarious groups like