Using Social Media Data to Explore Urban Land Value and Sentiment Inequality: A Case Study of Xiamen, China

Abstract

Differences in urban land values affect residents' living experiences and may contribute to sentiment inequality. Due to the popularity of smart mobile devices and social media platforms, online tweets with location information can be used as objective information to reflect sentiment differences of urban residents in different locations, overcoming the limitations of previous studies with small sample sizes or a lack of spatial information. Sentiment quantification based on deep learning enables the identification of spatial patterns of urban residents' sentiments. It also provides a new approach for analyzing data from big data platforms using an intelligent computing platform. This paper quantitatively analyzes the sentiment contained in social media tweets using a deep learning sentiment analysis algorithm to reveal inequalities between urban residents' sentiments and land values. The Baidu Intelligent Cloud sentiment analysis platform is used to identify 460,000 Weibo tweets in Xiamen, China, in 2020. We quantitatively analyze the positive and negative sentiments of residents and create a spatial distribution map. The concentration curve indicates sentiment inequality and the impact of high land values on residents' sentiments. The positive sentiment concentration index (CI) and correlation analysis show that the CI value is 0.07, and significant sentiment inequality exists due to the high land value. The use of social media tweet data to analyze sentiment inequality provides a reference for future interdisciplinary research in psychology, urban planning, geography, and sociology. The proposed approach of analyzing social media data using an intelligent computing platform provides new insights into multiplatform data interaction in the context of the Internet of Everything.