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.

Exploring the non-linear relationship and synergistic effect between urban built environment and public sentiment integrating macro- and micro-level perspective: a case study in San Francisco

“…To get a better understand of the spatial characteristics of the distribution of the sentiment index and its spatial relationship with the urban environment, this study employed a 200 m × 200 m grid as a basic statistic unit, the sentiment index and the urban environment indicators in each cell were aggregated based on the averages. In addition, the grid with a small number of samples was deleted, and the average sentiment index of each grid was obtained based on the following formula to ensure the normal distribution of data and eliminate the influence of outliers ( Gai et al, 2022 ).…”

Using Social Media Text Data to Analyze the Characteristics and Influencing Factors of Daily Urban Green Space Usage—A Case Study of Xiamen, China

“…It was also found that floating population settlement spaces have a negative effect on the daytime touring experience of residents in UGSs, which may be because these spaces are commonly found on the outskirts of suburban and central urban areas. Moreover, floating populations often choose to live in low-cost locations where UGSs have low construction funds and poor quality, making it difficult for them to meet the recreational needs of residents [97]. The proportion of the floating population was found to be the only external urban form factor explanatory variable affecting the daytime touring experience, with each one standard deviation increase decreasing the daytime touring experience by 0.30 standard deviations.…”

“…Then, 10,000 points of SMTD were manually labeled with sentiments. Machine learning based on pre-trained samples teaches computers how to quantify sentiments in SMTD [97]. Unlike scoring methods, such as sentiment dictionaries and cloud sentiment analysis [89], the localized SKEP method is similar to human subjective thinking, and the method is reproducible.…”

“…The sentiment scores of the social media text had a range of [0, 1]. The actual meaning of the index is as follows: an increase of 0.01 indicates a 1% increase in the positive park sentiment of SMTD; the closer the value is to 1, the more positive the overall sentiment of the park [89,97]. The sentiment analysis preprocessing model has been shared at https://doi.org/10.6084/m9.figshare.21524391, accessed on 1 May 2023.…”

Sentiment analysis of Chinese game reviews based on SKEP

“…There are also some specific applications of SKEP used in this paper. Gai et al [18] used the SKEP pre-trained model provided by Baidu intelligent cloud sentiment analysis platform to identify 460,000 Weibo tweets from Xiamen, China in 2020 for studying inequalities between urban residents' sentiments and land values.…”