Abstract
Analyzing tourists’ perceptions of air quality is of great significance to the study of tourist experience satisfaction and the image construction of tourism destinations. In this study, using the web crawler technique, we collected 27,500 comments regarding the air quality of 195 of China’s Class 5A tourist destinations posted by tourists on Sina Weibo from January 2011 to December 2017; these comments were then subjected to a content analysis using the Gooseeker, ROST CM (Content Mining System) and BosonNLP (Natural Language Processing) tools. Based on an analysis of the proportions of sentences with different emotional polarities with ROST EA (Emotion Analysis), we measured the sentiment value of texts using the artificial neural network (ANN) machine learning method implemented through a Chinese social media data-oriented Boson platform based on the Python programming language. The content analysis results indicated that in the adaption stage in Sina Weibo, tourists’ perceptions of air quality were mainly positive and had poor air pollution crisis awareness. Objective emotion words exhibited a similarly high proportion as subjective emotion words, indicating that taking both objective and subjective emotion words into account simultaneously helps to comprehensively understand the emotional content of the comments. The sentiment analysis results showed that for the entire text, sentences with positive emotions accounted for 85.53% of the total comments, with a sentiment value of 0.786, which belonged to the positive medium level; the direction of the temporal “up-down-up” changes and the spatial pattern of high in the south and low in the north (while having little difference between the east and the west) were basically consistent with reality. A further exploration of the theoretical basis of the semi-supervised ANN approach or the introduction of other machine learning methods using different data sources will help to analyze this phenomenon in greater depth. The paper provides evidence for new data and methods for air quality research in tourist destinations and provides a new tool for air quality monitoring.
Highlights
Air quality, climate change and ozone depletion are three important indicators for assessing the sustainable development of the atmospheric environment [1], of which the first two have become major challenges in tourism development [2]
Note: OB represents the actual frequency of each word recognized in the Word document composed of all comments on tourism sites in Heilongjiang and Shanghai by tourists; GO represents the deviation between the word segmentation results through Gooseeker and the actual frequency; RO represents the deviation of ROST CM; BO represents the deviation of BosonNLP; ** represents positive subjective emotion words; * represents positive objective emotion words; represents negative subjective emotion words; represents negative objective emotion words; and non-emotional words are unlabeled
The results of the ROST EA analysis showed that in the sentences of comments on the air quality of China’s 195 Class 5A tourism destinations, those with positive emotions, neutral emotions and negative emotions accounted for 85.53%, 7.21% and 7.26%, respectively, of the total number of sentences, indicating that positive emotions dominated, negative emotions corresponded to a large proportion and should not be ignored, and neutral comments exhibited the lowest proportion; the comments posted by tourists on social media are mostly with emotional content
Summary
Climate change and ozone depletion are three important indicators for assessing the sustainable development of the atmospheric environment [1], of which the first two have become major challenges in tourism development [2]. Since the Office of the State Council issued the Action Plan for Air Pollution Prevention and Control in 2013, the Chinese government has made remarkable progress in air quality control, and significant improvements have been made in key areas [22]. China is both a major tourist destination and a social media superpower; tourists have been very keen on sharing a wide range of tourism content on social media [11]. We comprehensively and systematically summarized the features and patterns of the perception from three levels, i.e., macro, meso and micro levels; we made comparisons with cases from the United States to introduce a new research approach to this field and enrich the content system from points to area, providing implications for the control of air pollution crises
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
