Automated Tourism Path Recommendation System Using Convolutional Neural Network based Bidirectional Long Short-Term Memory

Text-based sentiment analysis approaches are widely applied in various domains, such as decision support systems. Numerous studies have been carried out on sentiment analysis methods, including the use of complicated neural networks and word frequency or morphological analysis approaches. However, the sentimental analysis-based tourism recommendation models are suffered from the could start problem in this paper, developed the Deep Learning based tourism recommendation system using Convolution Neural Network with Bidirectional Long Short-Term Memory (CNNBiLSTM). Initially the collected dataset is pre-processed by various techniques and normalized the columns presented in the dataset. The CNN model is used to extract various information and BiLSTM is used to predict similar words. Effective word embedding is utilized for preventing the existing limitations. The proposed model is comparing with the exiting models and its archives the promising results the model was evaluated on different metrices Root Mean Square Error (RMSE) of 0.85 Mean Absolute Percentage Error (MAPE) of 1.49, Mean Absolute Error (MAE) of 0.83 and Mean Square Error (MSE) of 1.45 the existing models namely Autoencoder-based multi-criteria recommendation algorithm (AEMC) Tourism recommendation system using CNN-LSTM and Personalized Travel Route Recommendation-Deep learning algorithm (PTRR-DL).