A comprehensive project on sentiment scoring of 90,000 Amazon appliance products users’ reviews with VADER, RoBERTa, and Google API techniques. The individual model's scoring was verified with the True sentiment score, and The Google API outperformed with a 98% F1-Score. However, due to the stronger correlation of RoBERTa scores with true sentiment score, it was decalred as most appropriate and applied on entire dataset. Indentified the the products with 33% and more negative reviews from the popualtion.