Dataset: This contains all the datasets in JSON format that have been used in the research. In each JSON file, keys are the IDs of the open review paper, and the values are the reviews of it.Embeddings: This contains the embeddings of the dataset created from the open-ai text-embedding-3-small modelDictionaries: This contains the dictionaries that have been used in our token-frequency model
To regenerate the results of our paper, you just have to run the files: Our_RR_model.ipynb and our_TF_model.ipynb