Which factors influence public perceptions of urban attractions? — A comparative study
To better serve the public, urban attractions must understand the public's likes and dislikes and continually adapt and optimize their service in response. However, traditional methods for gauging public opinion, such as questionnaires and individual interviews, cannot meet the need for large-s...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2023-10-01
|
| Series: | Ecological Indicators |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S1470160X23006830 |
| _version_ | 1827816073625337856 |
|---|---|
| author | Zhonglin Tang Yihui Zhao Min Fu Yuting Wang Jingyue Xue |
| author_facet | Zhonglin Tang Yihui Zhao Min Fu Yuting Wang Jingyue Xue |
| author_sort | Zhonglin Tang |
| collection | DOAJ |
| description | To better serve the public, urban attractions must understand the public's likes and dislikes and continually adapt and optimize their service in response. However, traditional methods for gauging public opinion, such as questionnaires and individual interviews, cannot meet the need for large-scale, time-efficient, and high-precision public preference surveys: only large volumes of online tourist review data will suffice. This study takes Beijing and Shenzhen, the two top-tier cities in North and South China, as subjects to conduct an online review of visitor data for urban attractions in the two cities. Specifically, the influence of attraction features on public perception is quantitatively analyzed from three dimensions—spatial, temporal and resource type—which are combined with Natural Language Processing (NLP), Textual Data Mining, and Econometric analysis. The results show that the influence of four types of features—First impression, Economical, Service and Environmental features—on public perception remains largely consistent under different model conditions. However, different landscape types and attributes affect preferences in different ways. To be precise, water has radically different effects on public preferences in the north and south, with water features in urban attractions in the south contributing less to positive public perceptions. Meanwhile, water features significantly increase preferences for natural landscapes. Furthermore, public perceptions were found to be heavily influenced by public health emergencies (COVID-19). In the two cities studied, the proportion of positive reviews was higher after 2020 than before, as were the regression model indices. Drawing on these results, several suggestions are put forward for the optimization and adaptation of urban attractions. |
| first_indexed | 2024-03-12T00:09:42Z |
| format | Article |
| id | doaj.art-013a67c47672454896e8265196321307 |
| institution | Directory Open Access Journal |
| issn | 1470-160X |
| language | English |
| last_indexed | 2024-03-12T00:09:42Z |
| publishDate | 2023-10-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Ecological Indicators |
| spelling | doaj.art-013a67c47672454896e82651963213072023-09-16T05:29:14ZengElsevierEcological Indicators1470-160X2023-10-01154110541Which factors influence public perceptions of urban attractions? — A comparative studyZhonglin Tang0Yihui Zhao1Min Fu2Yuting Wang3Jingyue Xue4Research Center for Economy of Upper Reaches of the Yangtze River & School of Economics, Chongqing Technology and Business University, Chongqing, China; Institute for Regional Economic Studies, Chongqing Technology and Business University, Chongqing, China; Corresponding author at: Research Center for Economy of Upper Reaches of the Yangtze River & School of Economics, Chongqing Technology and Business University, Chongqing, China.Research Center for Economy of Upper Reaches of the Yangtze River & School of Economics, Chongqing Technology and Business University, Chongqing, ChinaSchool of Intelligent Manufacturing, Chongqing Industry Polytechnic College, Chongqing, ChinaResearch Center for Economy of Upper Reaches of the Yangtze River & School of Economics, Chongqing Technology and Business University, Chongqing, ChinaResearch Center for Economy of Upper Reaches of the Yangtze River & School of Economics, Chongqing Technology and Business University, Chongqing, ChinaTo better serve the public, urban attractions must understand the public's likes and dislikes and continually adapt and optimize their service in response. However, traditional methods for gauging public opinion, such as questionnaires and individual interviews, cannot meet the need for large-scale, time-efficient, and high-precision public preference surveys: only large volumes of online tourist review data will suffice. This study takes Beijing and Shenzhen, the two top-tier cities in North and South China, as subjects to conduct an online review of visitor data for urban attractions in the two cities. Specifically, the influence of attraction features on public perception is quantitatively analyzed from three dimensions—spatial, temporal and resource type—which are combined with Natural Language Processing (NLP), Textual Data Mining, and Econometric analysis. The results show that the influence of four types of features—First impression, Economical, Service and Environmental features—on public perception remains largely consistent under different model conditions. However, different landscape types and attributes affect preferences in different ways. To be precise, water has radically different effects on public preferences in the north and south, with water features in urban attractions in the south contributing less to positive public perceptions. Meanwhile, water features significantly increase preferences for natural landscapes. Furthermore, public perceptions were found to be heavily influenced by public health emergencies (COVID-19). In the two cities studied, the proportion of positive reviews was higher after 2020 than before, as were the regression model indices. Drawing on these results, several suggestions are put forward for the optimization and adaptation of urban attractions.http://www.sciencedirect.com/science/article/pii/S1470160X23006830Public PerceptionUrban attractionNLPTextual Data MiningBinomial logit model |
| spellingShingle | Zhonglin Tang Yihui Zhao Min Fu Yuting Wang Jingyue Xue Which factors influence public perceptions of urban attractions? — A comparative study Ecological Indicators Public Perception Urban attraction NLP Textual Data Mining Binomial logit model |
| title | Which factors influence public perceptions of urban attractions? — A comparative study |
| title_full | Which factors influence public perceptions of urban attractions? — A comparative study |
| title_fullStr | Which factors influence public perceptions of urban attractions? — A comparative study |
| title_full_unstemmed | Which factors influence public perceptions of urban attractions? — A comparative study |
| title_short | Which factors influence public perceptions of urban attractions? — A comparative study |
| title_sort | which factors influence public perceptions of urban attractions a comparative study |
| topic | Public Perception Urban attraction NLP Textual Data Mining Binomial logit model |
| url | http://www.sciencedirect.com/science/article/pii/S1470160X23006830 |
| work_keys_str_mv | AT zhonglintang whichfactorsinfluencepublicperceptionsofurbanattractionsacomparativestudy AT yihuizhao whichfactorsinfluencepublicperceptionsofurbanattractionsacomparativestudy AT minfu whichfactorsinfluencepublicperceptionsofurbanattractionsacomparativestudy AT yutingwang whichfactorsinfluencepublicperceptionsofurbanattractionsacomparativestudy AT jingyuexue whichfactorsinfluencepublicperceptionsofurbanattractionsacomparativestudy |