Detecting cognitive presence in online learning environments helps understand and enhance educational interactions in online discussions. However, the lack of annotated data and class imbalance challenges building accurate machine-learning models for this task. This study explores the impact of oversampling techniques using GPT-4 and BERT for the automatic classification of cognitive presence in online discussion, aiming to address data scarcity and improve model generalization. We found that oversampling enhances classification accuracy and Cohen’s Kappa, reaching up to 0.59 and 0.40, respectively, for a small sample of the original dataset. These results highlight the potential of recent oversampling methods in improving the detection of cognitive presence, informing future research and practical applications in online education.