Analyzing online reviews of foreign tourists to destination attractions in China: a novel text mining approach

ABSTRACTIn recent years, China has been gradually improving its tourism services along with its economic development. Inbound tourism not only boosts the economy of China, but also creates issues and challenges for tourism administration. The purpose of this study is to develop a novel text mining approach that combines topic modeling and sentiment analysis for exploring the dynamic evolution of topic intensity of destination attractions and discovering the reasons for foreign tourists' dissatisfactions. To this end, we propose an LDA-based topic evolution model, develop a tourism-oriented VADER dictionary and introduce an integration method for screening negative reviews. Then, the approach was used to analyze 80,546 online travel reviews from foreign tourists on TripAdvisor for 10 popular destination attractions in China from 2011 to 2019. The findings can help tourism practitioners better understand the changes and trends of the topics over time as well as develop strategies with respect to tourists' dissatisfactions.KEYWORDS: Destination attractionstopic modelingdissatisfaction analysisonline travel reviewstext miningsentiment analysis Data availability statementData can be made available on request.Disclosure statementNo potential conflict of interest was reported by the author(s).Notes1 Available at https://www.topchinatravel.com/china-guide/china-tourism/2 Available at https://www.mct.gov.cn/whzx/ggtz/202006/t20200620_872735.htm3 Available at http://wta.dragongap.cn/wp-content/uploads/2021/05/2019-WTA-Data-Analysis-Report-of-Chinas-Inbound-Tourism.pdf4 GSDMM is a collapsed Gibbs Sampling algorithm for the Dirichlet Multinomial Mixture model.5 https://github.com/cjhutto/vaderSentiment6 https://github.com/cjhutto/vaderSentiment/blob/master/vaderSentiment/vader_lexicon.txtAdditional informationFundingThis work was supported by the National Natural Science Foundation of China [grant number 71871050, 72271047, 72031002].