Exploring the Relationship between Urban Youth Sentiment and the Built Environment Using Machine Learning and Weibo Comments

Abstract

As the relationship between the built environment and the sense of human experience becomes increasingly important, emotional geography has begun to focus on sentiments in space and time and improving the quality of urban construction from the perspective of public emotion and mental health. While youth is a powerful force in urban construction, there are no studies on the relationship between urban youth sentiments and the built environment. With the development of the Internet, social media has provided a large source of data for the metrics of youth sentiment. Based on data from more than 10,000 geolocated Sina Weibo comments posted over one week (from 19 to 25 July 2021) in Shanghai and using a machine learning algorithm for attention mechanism, this study calculates the sentiment label and sentiment intensity of each comment. Ten elements in five aspects were selected to assess the built environment at different scales and also to explore the correlations between built environment elements and sentiment intensity at different scales. The study finds that the overall sentiment of Shanghai youth tends to be negative. Sentiment intensity is significantly associated with most built environment elements at smaller scales. Urban youth have a higher proportion of both happy and sad sentiments, within which sad sentiments are more closely related to the built environment and are significantly related to all built environment elements. This study uses a deep learning algorithm to improve the accuracy of sentiment classification and confirms that the built environment has a great impact on sentiment. This research can help cities develop built environment optimization measures and policies to create positive emotional environments and enhance the well-being of urban youth.

Trajectories of and spatial variations in HPV vaccine discussions on Weibo, 2018-2023: a deep learning analysis

“…Social media users tend to be younger, however, exactly aligning with the target population for HPV vaccination. 6 Second, our analyses are based on individual posts instead of social media users. Future research may develop innovative computational algorithms to analyze at the individual user level by incorporating users’ profiles and historical posts.…”

“…5 As social media becomes popular, the young generation posts massive discussions about HPV vaccine on social media, which may drive changes in sexual norms and public attitudes towards the HPV vaccine. 6 In addition, few cities in China started to introduce HPV vaccines into local immunization programme since 2022, promoting public attention to HPV vaccine. 7 Therefore, it is imperative to investigate discussions on social media and its role in HPV vaccination.…”

Big Data, Decision Models, and Public Health

“…People’s sentiment and well-being are affected by the degree to which the physical environment meets their physical and psychological needs. The second paper, “ Exploring the Relationship between Urban Youth Sentiment and the Built Environment Using Machine Learning and Weibo Comments ”, by Duan et al [ 48 ], based on data from Sina Weibo comments posted in Shanghai and using the machine learning algorithm, calculated the sentiment label and sentiment intensity of each comment. In addition, there were ten elements in five aspects selected to assess the built environment at different scales and to explore the correlations between built environment elements and sentiment intensity at different scales.…”

Consumers’ Opinions towards Public Health Effects of Online Games: An Empirical Study Based on Social Media Comments in China

“…The study, data collected from a social media Weibo, examined opinions towards child abuse and made recommendations for the government to improve child protection policies [48]. From the perspective of public opinion about emotion and mental health towards the built environment, we explore geolocated Weibo comments to assess the built environment at different scales and to analyze the correlations between built environment elements and sentiment intensity at different scales [49]. Simultaneously, the digitalization form of comment text on social media relies on computer-assisted analytical techniques.…”

“…Based on social media comments, the diversity of NLP methods is revealed. All six primary NLP methods-text preprocessing, text representation, classification, topic modeling, emotion analysis, and deep learning-are applied in public health studies [44][45][46][47][48][49]. The above studies show that social media comments and NLP methods have given researchers unprecedented opportunities to harvest a wealth of textual data materials and advanced technology for investigating contemporary public health phenomena.…”