Social Media Data-Based Sentiment Analysis of Tourists’ Air Quality Perceptions

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.

Dynamic Evolution of Public’s Positive Emotions and Risk Perception for the COVID-19 Pandemic: A Case Study of Hubei Province of China

“…It will not be affected by the public subjective level, so the data quality is higher. Similarly, Tao et al used the comments and search data in social media to analyze the relationship in tourist satisfaction and air quality in the scenic area, providing a reference for scenic area management [56].…”

Sentiment Analysis to Measure Quality and Build Sustainability in Tourism Destinations

“…A great qualitative and quantitative leap has occurred in recent years as a result of two effects [19,26,33,34]. The first is the use of large amounts of e-WoM data that offer more quantitative and qualitative information than data that are traditionally obtained through surveys and other official data sources.…”

“…Researchers use a very limited number of tourism databases, which are namely, Tri-pAdvisor (tool NLTK), Expedia, Booking, Airbnb, Twitter, Amazon, Facebook or Academic Yelp Dataset [2,35,37]. In the case of tourism databases in China, these are obtained from the main OTAs and the social networks used there [3,33,35,36,38]: Baidu Travel, Ctrip Travel, Tongcheng Travel, Qunar Travel, Tu Niu, Qiong You, and Sina Weibo. As a result of these limitations, studies in this area are usually limited to a certain tourist spot or a specific area, and there only a few cases where an investigation has focused on cross-cutting aspects that affect several countries [2,7].…”

“…The second limitation is the methodology. The four most commonly used methodologies are dictionary-based methods, machine learning methods, deep learning methods, and hybrids of previous methods [2,33,[35][36][37][38][39]. All methodologies require the use of multiple combined technologies, the use of large unstructured databases, and the difficult reduction and acquisition of results.…”

Machine Learning Aided Tracking Analysis of Haze Pollution and Regional Heterogeneity

“…Previous studies found that both haze and tourism flows can be spatially dispersed, affecting local and adjacent areas and creating spatial spillover effects [9][10][11][12]. Air pollution slows down the development of tourism [13][14][15][16], but it is unclear whether this negative effect is significant. For example, in the practice of tourism development in mainland China, there is no significant evidence that haze pollution is negatively correlated with local tourism development.…”