Research on Sentiment Classification of Tourist Destinations Based on Convolutional Neural Network

Abstract

Smart tourism has recently received widespread attention from academia and practitioners. The concept aims to improve the tourism experience and increase the competitiveness of destinations based on the development of technologies such as the Internet, communications, and big data. In order to cope with the industry development challenges brought by personalized tourism in the era of big data, this paper uses the text of online travel notes with Guizhou as the destination as the data source, and proposes a travel destination review sentiment classification model based on convolutional neural network. Compared with several other machine learning models, this model has the highest accuracy of emotion classification, reaching 91.6%, and it has a very good effect on text emotion classification.