This project focuses on designing and implementing a deep learning model from scratch using Keras and LSTM networks to analyze customer sentiment in the airline industry. The model achieves an accuracy of 86.39% in predicting whether a customer review is positive or negative, based on the likelihood of recommendation. It includes a comprehensive text preprocessing pipeline and features an LSTM-based architecture enhanced with batch normalization and dropout layers for regularization. Hyperparameter tuning is conducted through random search.
