Analysis and Application of Tourists’ Sentiment Based on Hotel Comment Data

In today’s life, Online Travel Agency (OTA) platform gets more and more users. Tourists on OTA platform makes much more comments on hotels. Similarly, the authenticity also increases significantly. Real user feedback plays a guiding role in improving the quality of the hotel, but it needs to obtain useful information from the complex comment data and a series of data analysis processes. In this paper, the ‘Bazhuayu’ collector is used to gain data, making pre-processing of the dataset. Using jieba to finish segmentation. The Term Frequency-Inverse Document Frequency algorithm is used to extract keywords, and then the Bag-of-Words model is used to construct the word vector. Finally, subsampled is used to balance the dataset. The support vector machine, Naive Bayes and Long Short-Term Memory neural network model are established to classify and adjust the parameters, compare the classification performance of the models, put forward some suggestions for hotel self optimization and upgrading according to the classification result.