Aspect-based sentiment analysis for hotel reviews using an improved model of long short-term memory

Advances in information technology have given rise to online hotel reservation options. The user review feature is an important factor during the booking of hotels. Generally, most service providers provide and rating features for assessing However, not all or recap reviews every aspect services offered. Therefore, we propose a method summarise based on multiple aspects, including food, room, service, location. This uses long short-term memory (LSTM), together with hidden layers automation optimal number neurons. F1-measure value 75.28% best model was fact that (i) size first layer 1,200 neurons tanh activation function, (ii) second 600 ReLU function. proposed outperforms baseline (also known as standard LSTM) by 10.16%. It anticipated developed through this study can be accessed users acquire more specific aspects offered hotels