Read our paper

Listen to the podcast on YouTube

Dataset and Code Descriptions

• Training_AE – Fine-tuning dataset for GPT-3.5 to extract aspects (AE).
• Training_CC – Fine-tuning dataset for GPT-3.5 to classify aspects (CC).
• Testing_all_variables – Comprehensive testing dataset containing review texts, metadata, and all statistical analysis variables.
• Testing_analysis – Testing dataset for statistical analysis.
• RoBERTa_eval_data – Evaluation dataset extracted from the training data for model assessment.
• Code_SMR – Python code executed on Google Colab for performing all study analyses.