The document describes a study that analyzes customer reviews on Twitter about hotels using deep learning techniques. Twitter data is collected using Python's Tweepy library and preprocessed by removing noise like retweets, URLs and hashtags. The data is then split using scikit-learn into training, validation and testing sets. Tokenization is performed to convert text to vectors and sentiment analysis is done using techniques like Bi-Sense Emoji Embedding (BSEE), Random Forest (RF) and Support Vector Machine (SVM). The performance of BSEE is compared based on accuracy, recall, precision and time taken and is found to provide better results.