Urban Recreational Space Heat-Emotion Distribution and Matching Pattern Based on Machine Learning: A Case Study of Guangzhou City
Received date: 2024-04-03
Revised date: 2024-08-23
Online published: 2025-07-21
Recreational spaces play a pivotal role in enhancing the quality of national life, fostering physical and mental health, and promoting social interaction. While previous research has predominantly examined the supply side of urban recreational spaces, there is a noticeable gap in the characterization of these spaces based on societal perceptions. Using Guangzhou as a case study, this study harnesses big data sourced from Ma Feng Wo and Ctrip. Based on machine learning techniques, it discerns recreational emotions and synergizes Geographic Information System (GIS) spatial analysis with heat-emotion matching analysis. This approach facilitates a nuanced and precise examination of the structural and experiential characteristics of urban recreational spaces from the perspective of social perception. The objective of this study is to offer informed references for the strategic planning and management of urban recreational spaces. The findings indicate that: (1) The distribution of recreational spaces in Guangzhou exhibits a "core agglomeration, edge dispersion" pattern, characterized by a "one core, multiple centers" configuration. Notably, the central urban region and its proximate suburbs—specifically, the Panyu, Baiyun, and Huangpu Districts—show a marked concentration in both the number and popularity of recreational spaces. In contrast, peripheral urban zones primarily feature government residences, premium ecological recreational spaces, and hot spring resources. These areas—including the Huadu, Conghua, and Zengcheng urban areas, Conghua District's hot spring town, and Paitan town—stand out as secondary hubs in terms of recreational space concentration and popularity. Moreover, recreational spaces situated along waterfronts and in areas with dense road networks tend to follow a "point-axis" distribution model, with a staggering 90.45% of these spaces located within a 1 km radius of the road network. (2) The overall approval rate of urban recreational spaces in Guangzhou is significantly high, evidenced by an average positive emotion ratio of 86.99%. However, there is a marked polarization in terms of popularity, manifesting as a "core-edge" decline in spatial distribution. Recreational spaces that evoke predominantly positive emotions are primarily located in the city center and are proximate to the administrative seats of the Panyu, Baiyun, Huangpu, and Nansha Districts. These areas also record a low ratio of negative emotions. In contrast, neutral and negative emotions are more prevalent in the commercial streets and pedestrian zones of the central city, as well as the suburbs of the Conghua, Huadu, and Zengcheng Districts. A considerable emphasis on "cost performance" is observed across all emotional categories related to Guangzhou's urban recreational spaces, indicating a widespread concern among tourists/residents regarding the balance between the costs of these spaces and their service quality. (3) The congruence between popularity and emotional response in Guangzhou's urban recreational spaces is suboptimal. Spatially, this disconnect can be categorized into three distinct types: the "polarized" pattern in the central city, the "experience enhancement" pattern in the Huadu, Panyu, Baiyun, and Conghua Districts, and the "insufficient supply" pattern in the Zengcheng, Huangpu, and Nansha Districts. These findings provide valuable insights for metropolitan areas aiming to refine the layout and management of recreational spaces. By understanding social demands and experiences, cities can craft a more optimized group perception of urban recreational spaces, thereby enhancing tourists' satisfaction and elevating the well-being of residents.
Fuyuan Wang , Zhiyu Zhang , Yuanjing Xie , Xinyi Yang , Miao Sun . Urban Recreational Space Heat-Emotion Distribution and Matching Pattern Based on Machine Learning: A Case Study of Guangzhou City[J]. Tropical Geography, 2025 , 45(7) : 1174 -1188 . DOI: 10.13284/j.cnki.rddl.20240202
表1 广州市城市游憩空间情感描述性统计Table 1 Descriptive statistics of urban recreational space sentiment in Guangzhou |
统计指标 | 好评率 | 中评率 | 差评率 | |
---|---|---|---|---|
样本数量/个 | 398 | 398 | 398 | |
最大值/% | 100.00 | 14.29 | 47.37 | |
最小值/% | 44.74 | 0.00 | 0.00 | |
平均值/% | 86.99 | 4.24 | 8.78 | |
标准差 | 0.09 | 0.03 | 0.08 | |
百分位数/% | 25 | 82.35 | 2.00 | 2.63 |
50 | 88.57 | 4.00 | 6.48 | |
75 | 95.00 | 6.25 | 12.03 |
表2 消极评价关键词TOP20及TF-IDF值Table 2 TOP20 keywords of negative reviews and TF-IDF values |
序号 | 特征 | TF-IDF | 序号 | 特征 | TF-IDF |
---|---|---|---|---|---|
1 | 性价比 | 0.111 35 | 11 | 前台 | 0.055 01 |
2 | 设施 | 0.095 90 | 12 | 服务态度 | 0.051 65 |
3 | 工作人员 | 0.094 56 | 13 | 特色 | 0.050 66 |
4 | 垃圾 | 0.079 11 | 14 | 酒店 | 0.048 99 |
5 | 收费 | 0.069 21 | 15 | 免费 | 0.048 82 |
6 | 排队 | 0.067 41 | 16 | 房间 | 0.048 26 |
7 | 服务 | 0.062 81 | 17 | 大家 | 0.045 22 |
8 | 环境 | 0.059 32 | 18 | 热水 | 0.043 44 |
9 | 小孩 | 0.058 29 | 19 | 不值 | 0.041 51 |
10 | 坑人 | 0.057 42 | 20 | 朋友 | 0.039 80 |
表3 中立评价关键词TOP20及TF-IDF值Table 3 TOP20 keywords of neutral reviews and TF-IDF values |
序号 | 特征 | TF-IDF | 序号 | 特征 | TF-IDF |
---|---|---|---|---|---|
1 | 性价比 | 0.094 04 | 11 | 小孩 | 0.042 88 |
2 | 免费 | 0.077 96 | 12 | 收费 | 0.038 63 |
3 | 设施 | 0.073 82 | 13 | 交通 | 0.036 86 |
4 | 环境 | 0.073 05 | 14 | 樱花 | 0.034 51 |
5 | 特色 | 0.068 9 | 15 | 参观 | 0.032 84 |
6 | 建筑 | 0.065 68 | 16 | 博物馆 | 0.032 65 |
7 | 地铁 | 0.059 89 | 17 | 历史 | 0.032 06 |
8 | 风景 | 0.054 27 | 18 | 趣味 | 0.031 10 |
9 | 散步 | 0.046 37 | 19 | 水乡 | 0.027 26 |
10 | 广场 | 0.045 32 | 20 | 步行街 | 0.025 78 |
表4 积极评价关键词TOP20及TF-IDF值Table 4 TOP20 keywords of positive reviews and TF-IDF values |
序号 | 特征 | TF-IDF | 序号 | 特征 | TF-IDF |
---|---|---|---|---|---|
1 | 环境 | 0.090 48 | 11 | 环境优美 | 0.041 35 |
2 | 免费 | 0.075 95 | 12 | 交通 | 0.041 11 |
3 | 建筑 | 0.064 67 | 13 | 博物馆 | 0.038 24 |
4 | 特色 | 0.062 19 | 14 | 很漂亮 | 0.037 58 |
5 | 性价比 | 0.059 88 | 15 | 设施 | 0.035 26 |
6 | 风景 | 0.058 45 | 16 | 空气 | 0.033 14 |
7 | 广场 | 0.048 31 | 17 | 参观 | 0.031 67 |
8 | 小孩 | 0.043 44 | 18 | 朋友 | 0.030 12 |
9 | 历史 | 0.043 40 | 19 | 酒店 | 0.029 88 |
10 | 散步 | 0.042 72 | 20 | 地铁 | 0.029 63 |
Aparicio D, Martín-Caro M S H, García-Palomares J C, and Gutiérrez J. 2022. Exploring the Spatial Patterns of Visitor Expenditure in Cities Using Bank Card Transactions Data. Current Issues in Tourism, 25(17): 2770-2788.
|
Cheng Y, Browning M H, Zhao B, Qiu B, Wang H, and Zhang J. 2024. How Can Urban Green Space be Planned for a 'Happy City'? Evidence from Overhead-To Eye-Level Green Exposure Metrics. Landscape and Urban Planning, 249: 105131.
|
Chow B C, McKenzie T L, and Sit C H P. 2016. Public Parks in Hong Kong: Characteristics of Physical Activity Areas and Their Users. International Journal of Environmental Research and Public Health, 13(7): 639.
|
Curry N and Ravenscroft N. 2001. Countryside Recreation Provision in England: Exploring A Demand-Led Approach. Land Use Policy, 18(3): 281-291.
|
樊亚明,田丽莹,陈昭宇. 2023. 城市生态游憩空间可达性评价及规划响应——以桂林市为例. 规划师,39(2):125-132.
Fan Yaming, Tian Liying, and Chen Zhaoyu. 2023. Evaluation and Planning Response of Ecological Recreational Space Accessibility. Planners, 39(2): 125-132.
|
Fisher D M, Wood S A, Roh Y H, and Kim C K. 2019. The Geographic Spread and Preferences of Tourists Revealed by User-Generated Information on Jeju Island, South Korea. Land, 8(5): 73.
|
广州市人民政府. 2024. 广州市人民政府关于印发广州市国土空间总体规划(2021—2035年)的通知. (2024-11-06) [2025-06-29]. https://www.gz.gov.cn/zwgk/fggw/szfwj/content/post_9960352.html. [Guangzhou Municipal People's Government. 2024. Notice of the Guangzhou Municipal People's Government on Issuing the Guangzhou Land and Space Master Plan(2021-2035). (2024-11-06) [2025-06-29]. https://ghzyj.gz.gov.cn/zwgk/ztzl/gtkjgh/gzxx/content/post_6484475.html. ]
|
广州市统计局,国家统计局广州调查队. 2022. 2022广州统计年鉴. 北京:中国统计出版社.
Guangzhou Bureau of Statistics and National Bureau of Statistics Guangzhou Survey Team. 2022. Guangzhou Statistical Yearbook 2022. Beijing: China Statistics Press.
|
郭佳怡,方博平,陆欣怡,王妮,宋涛. 2023. 基于文本挖掘和情感分析方法的“智慧旅游”服务质量感知研究. 现代信息科技,7(6):1-5,12.
Guo Jiayi, Fang Boping, Lu Xinyi, Wang Ni, and Song Tao. 2023. Research on Service Quality Perception of "Smart Tourism" Analysis Methods Based on Text Mining and Sentiment. Modern Information Technology, 7(6): 1-5, 12.
|
Guo S H, Yang G G, Pei T, Ma T, Song C, Shu H, Du Y Y, and Zhou C H. 2019. Analysis of Factors Affecting Urban Park Service Area in Beijing: Perspectives From Multi-Source Geographic Data. Landscape and Urban Planning, 181: 103-117.
|
Guo X, Tu X, Huang G, Fang X, Kong L, and Wu J. 2022. Urban Greenspace Helps Ameliorate People's Negative Sentiments During the COVID-19 Pandemic: The Case of Beijing. Building and Environment, 223: 109449.
|
侯玉霞,吴忠军. 2018. 基于国内外游客IPA分析的民族特色主题民宿转型升级研究——以龙胜各族自治县平安寨、大寨为例. 社会科学家,(5):72-80.
Hou Yuxia and Wu Zhongjun. 2018. Research on the Transformation and Upgrading of Ethnic Themed Homestays Based on IPA Analysis of Domestic and Foreign Tourists: Taking Ping'anzhai and Dazhai in Longsheng Autonomous County As Examples. Social Scientist, (5): 72-80.
|
Kim Y, Kim C K, Lee D K, Lee H W and Andrada R T. 2019. Quantifying Nature-Based Tourism in Protected Areas in Developing Countries By Using Social Big Data. Tourism Management, 72: 249-256.
|
Lai S and Deal B. 2022. Parks, Green Space, and Happiness: A Spatially Specific Sentiment Analysis Using Microblogs in Shanghai, China. Sustainability, 15(1): 146.
|
黎雅悦,戈大专,牛博,李杰. 2022. 广州市休闲旅游资源空间分布及其可达性特征. 热带地理,42(10):1701-1712.
Li Yayue, Ge Dazhuan, Niu Bo, and Li Jie. 2022. Accessibility and Structural Characteristics of Leisure Tourism Resources in Guangzhou. Tropical Geography, 42(10): 1701-1712.
|
廖奇. 2006. 游憩空间之于人的价值——社会和谐发展的跨学科思考. 自然辩证法研究,(3):102-104.
Liao Qi. 2006. Value of Recreation Space to the People Multidisciplinary Consideration on the Harmonious Development of Society. Studies in Dialectics of Nature, (3): 102-104.
|
Li J, Gao J, Zhang Z, Fu J, Shao G, Zhao Z and Yang P. 2024. Insights into Citizens' Experiences of Cultural Ecosystem Services in Urban Green Spaces Based on Social Media Analytics. Landscape and Urban Planning, 244: 104999.
|
刘雷. 2012. 合肥城市游憩空间分布特征及品质评价研究. 合肥:安徽建筑工业学院.
Liu Lei. 2012. Research on Spatial Distribution Characteristics and Quality Evaluation of Urban Recreation Space in Hefei. Hefei: Anhui University of Architecture.
|
Liu R and Xiao J. 2021. Factors Affecting Users' Satisfaction with Urban Parks through Online Comments Data: Evidence from Shenzhen, China. International Journal of Environmental Research and Public Health, 18(1): 253.
|
刘一鸣,黄彦瑜,赖妙华,龚华. 2023. 广州城市人口空间结构与演化趋势研究. 人口与发展,29(2):41-50.
Liu Yiming, Huang Yanyu, Lai Miaohua, and Gong Hua. 2023. Study on the Spatial Structure and Evolutionary Trends of Guangzhou Urban Population. Population and Development, 29(2): 41-50.
|
刘瑜. 2016. 社会感知视角下的若干人文地理学基本问题再思考. 地理学报,71(4):564-575.
Liu Yu. 2016. Revisiting Several Basic Geographical Concepts: A Social Sensing Perspective. Acta Geographica Sinica, 71(4): 564-575.
|
刘瑜. 2024. 遥感与地理信息系统研究所刘瑜教授成果入选2023年度“中国地理科学十大研究进展”.(2024-04-27)[2024-07-07]. https://irsgis.pku.edu.cn/xwdt/158210.htm.
Liu Yu. 2024. The Institute of Remote Sensing and Geographic Information System at Peking University. The Research Achievements of Professor Liu Yu from the Institute of Remote Sensing and Geographic Information System have been Selected as One of the "Top Ten Research Advances in Chinese Geographic Sciences" for the Year 2023. (2024-04-27) [2024-07-07]. https://irsgis.pku.edu.cn/xwdt/158210.htm.
|
刘震,戴泽钒,楼嘉军,刘松. 2019. 基于数字足迹的城市游憩行为时空特征研究——以上海为例. 世界地理研究,28(5):95-105.
Liu Zhen, Dai Zefan, Lou Jiajun, and Liu Song. 2019. Temporal and Spatial Characteristics of Urban Recreation Behavior Based on Digital Footprints—A Case Study of Shanghai. World Regional Studies, 28(5): 95-105.
|
McConnachie M M and Shackleton C M. 2010. Public Green Space Inequality in Small Towns in South Africa. Habitat International, 34(2): 244-248.
|
秦学. 2003. 城市游憩空间结构系统分析——以宁波市为例. 经济地理,23(2):267-271,288.
Qin Xue. 2003. Systematic Study on Urban Recreational Spatial Structure—A Case Study of Ningbo City. Economic Geography, 23(2): 267-271, 288.
|
时少华,吴泰岳,李享,范怡然. 2022. 基于ITCM和CVM的运河公园游憩价值评估研究——以北京通州大运河森林公园为例. 干旱区资源与环境,36(1):201-208.
Shi Shaohua, Wu Taiyue, Li Xiang, and Fan Yiran. 2022. Assessment of Recreation Value of Tongzhou Grand Canal Forest Park, Beiing Based on ITCM and CVM. Journal of Arid Land Resources and Environment, 36(1): 201-208.
|
Salton G and Yu C T. 1973. On the Construction of Effective Vocabularies for Information Retrieval. Acm Sigplan Notices, 10(1): 48-60.
|
Shoval N, Schvimer Y, and Tamir M. 2018. Tracking Technologies and Urban Analysis: Adding the Emotional Dimension. Cities, 72: 34-42.
|
Sinclair M, Mayer M, Woltering M, and Ghermandi A. 2020. Using Social Media to Estimate Visitor Provenance and Patterns of Recreation in Germany's National Parks. Journal of Environmental Management, 263: 110418.
|
孙琨,钟林生,张爱平,张国平. 2016. 城市生态游憩空间休闲价值对比分析——以常熟市为例. 地理研究,35(2):256-270.
Sun Kun, Zhong Linsheng, Zhang Aiping, and Zhang Guoping. 2016. Comparative Analysis on the Leisure Values of Urban Ecological Recreation Spaces: A Case Study of Changshu City. Geographical Research, 35(2): 256-270.
|
Tang T, Huang L, and Chen Y. 2020. Evaluation of Chinese Sentiment Analysis APIs Based on Online Reviews. In: IEEE. 2020 IEEE International Conference on Industrial Engineering and Engineering Management(IEEM).Singapore: The Institute of Electrical and Electronics Engineers, 923-927.
|
Volo S. 2021. The Experience of Emotion: Directions for Tourism Design. Annals of Tourism Research, 86: 103097.
|
王甫园,王开泳,虞虎,陈田. 2020. 珠三角城市群生态游憩空间分异特征及关联性因素. 地理研究,39(9):2148-2164.
Wang Fuyuan, Wang Kaiyong, Yu Hu, and Chen Tian. 2020. Spatial Differentiation and Correlative Factors of Ecological Recreation Space Distribution in the Pearl River Delta urban agglomeration. Geographical Research, 39(9): 2148-2164.
|
王甫园,王开泳,郑鑫,林明水. 2021. 珠三角城市群生态空间游憩利用扩展格局及影响因素. 生态学报,41(17):7049-7062.
Wang Fuyuan, Wang Kaiyong, Zheng Xin, and Lin Mingshui. 2021. Spatial Expansion Pattern and Influencing Factors of Recreational Utilization of Ecological Space in the Pearl River Delta Urban Agglomeration. Acta Ecologica Sinica, 41(17): 7049-7062.
|
王甫园,张之羽. 2023. 2000—2020年北京市生态游憩空间分布格局演变. 中国生态旅游,13(6):1077-1095.
Wang Fuyuan and Zhang Zhiyu. 2023. Distribution and Evolution Pattern of Ecological Recreation Space in Beijing from 2000 to 2020. Journal of Chinese Ecotourism, 13(6): 1077-1095.
|
王润,黄凯,朱鹤. 2015. 国内外城市游憩用地管理与研究动态. 华中农业大学学报(社会科学版),(3):94-101.
Wang Run, Huang Kai, and Zhu He. 2015. Review of Domestic and Overseas Research on Urban Recreational Land. Journal of Huazhong Agricultural University(Social Sciences Edition), (3): 94-101.
|
吴志强,吴承照. 2005. 城市旅游规划原理. 北京:中国建筑工业出版社.
Wu Zhiqiang and Wu Chengzhao. 2005. Urban Recreation and Tourism Planning Studies. Beijing: China Architecture & Building Press.
|
向博文,魏伟,赵渺希. 2022. 黄浦江核心区滨水游憩流空间结构特征研究. 上海城市规划,(6):104-110.
Xiang Bowen, Wei Wei, and Zhao Miaoxi. 2022. Spatial Structure Characteristics of Waterfront Recreation Flow in Core Area of the Huangpu River. Shanghai Urban Planning Review, (6): 104-110.
|
肖贵蓉,宋文丽. 2008. 城市游憩空间结构优化研究——以大连市为例. 中国人口·资源与环境,(2):86-92.
Xiao Guirong and Song Wenli. 2008. Structural Optimization of Urban Recreational Space in Dalian. China Population Resources and Environment, (2): 86-92.
|
Wang D, Brown G, and Liu Y. 2015. The Physical and Non-Physical Factors That Influence Perceived Access to Urban Parks. Landscape and Urban Planning, 133: 53-66.
|
徐琳琳,周彬,虞虎,张鹏飞. 2023. 2022年冬奥会对张家口城市旅游地形象的影响研究——基于UGC文本分析. 地理研究,42(2):422-439.
Xu Linlin, Zhou Bin, Yu Hu, and Zhang Pengfei. 2023. Research on the Influence of 2022 Winter Olympic Games on the Tourism Destination Image of Zhangjiakou: Based on UGC Text Analysis. Geographical Research, 42(2): 422-439.
|
Xu M, Chen Z, Zeng M, and Ke Y. 2024. Research on Landscape Preference of Urban Mountain Park Based on Visitors' Perception—Taking Xishan Park in Mianyang City as an Example. Open Journal of Social Sciences, 12(1): 469-485.
|
杨友宝,曹吕苗,李琪. 2021. 基于百度指数的长沙市居民游憩活动行为时空演变特征研究. 资源开发与市场,37(2):221-227.
Yang Youbao, Cao Lvmiao, and Li Qi. 2021. Research on the Spatiotemporal Evolution Characteristics of Recreational Activity Behavior Among Residents in Changsha City Based on Baidu Index. Resource Development & Market, 37(2): 221-227.
|
殷聪,张李义. 2018. 基于TF-IDF的情境后过滤推荐算法研究——以餐饮业O2O为例. 数据分析与知识发现,2(11):28-36.
Yin Cong and Zhang Liyi. 2018. Recommendation Algorithm for Post-Context Filtering Based on TF-LDF: Case Study of Catering O2O. Data Analysis and Knowledge Discovery, 2(11): 28-36.
|
尤众喜,华薇娜,潘雪莲. 2019. 中文分词器对图书评论和情感词典匹配程度的影响. 数据分析与知识发现,3(7):23-33.
You Zhongxi, Hua Weina, and Pan Xuelian. 2019. The Impact of Chinese Word Segmentation on The Matching Degree between Book Reviews and Sentiment Dictionaries. Data Analysis and Knowledge Discovery, 3(7): 23-33.
|
于冰沁,谢长坤,杨硕冰,车生泉. 2014. 上海城市社区公园居民游憩感知满意度与重要性的对应分析. 中国园林,30(9):75-78.
Yu Bingqin, Xie Changkun, Yang Shuobing, and Che Shengquan. 2014. Correspondence Analysis on Residents' Perceived Recreation Satisfaction and Importance in Shanghai Urban Community Park. Chinese Landscape Architecture, 30(9): 75-78.
|
张佳宝,乌恩. 2023. 基于游客感知价值的国家公园游憩功能研究——以黄石国家公园和武夷山国家公园为例. 世界地理研究,32(2):146-157.
Zhang Jiabao and Wu En. 2023. Recreation Function in National Parks Based on Tourists' Perceived Value: Two Case Studies of Yellowstone National Park and Wuvishan National Park. World Regional Studies, 32(2): 146-157.
|
Zhang W, Yoshida T, and Tang X. 2011. A comparative study of TF* IDF, LSI and Multi-Words for Text Classification. Expert Systems with Applications, 38(3): 2758-2765.
|
Zhang J, Liu L, Wang J, Dong D, Jiang T, Chen J, and Ren Y. 2024. Exploring the Relationship between the Sentiments of Young People and Urban Green Space by Using a Check-In Microblog. Forests, 15(5): 796.
|
张静,卢松,段鹏霄,孙颖,胡凯霖. 2022. 媒体数据在西方旅游学中的应用研究进展. 中国生态旅游,12(3):374-385.
Zhang Jing, Lu Song, Duan Pengxiao, Sun Ying, and Hu Kailin. 2022. Review on the Application of Media Data in Western Tourism Studies. Journal of Chinese Ecotourism, 12(3): 374-385.
|
Zhou H, Chi X, Norman R, Zhang Y, and Song C. 2024. Tourists' Urban Travel Modes: Choices for Enhanced Transport and Environmental Sustainability. Transportation Research Part D: Transport and Environment, 129: 104144.
|
周源,刘怀兰,杜朋朋,廖岭. 2017. 基于改进TF-IDF特征提取的文本分类模型研究. 情报科学,35(5):111-118.
Zhou Yuan, Liu Huailan, Du Pengpeng, and Liao Ling. 2017. Research on Text Classification Model Based on Improved TF-IDF Feature Extraction. Information Science, 35(5): 111-118.
|
Zhu J and Xu C. 2021. Sina Microblog Sentiment in Beijing City Parks as Measure of Demand for Urban Green Space During the COVID-19. Urban Forestry & Urban Greening, 58: 126913.
|
Zhu Z, Liang J, Li D, Yu H, and Liu G. 2019. Hot Topic Detection Based on a Refined TF-IDF Algorithm. IEEE Access, 7: 26996-27007.
|
Zou N, Mi X, Xiao Y, Li Y, and Hu N. 2024. Assessing Urban Park Equity in Chaoyang District, Beijing Using Online Review Data. Scientific Reports, 14(1): 1160.
|
/
〈 |
|
〉 |