| 摘要: |
| 城市公园是城市空间的重要部分，在生态、社会和经济等方面至关重要。园林植物作为主要物质空间要素，对公众身心健康有着积极的恢复和促进作
用。但基于公众视角与用户生成数据对园林植物感知行为及偏好特征的深入研究较少。以武汉城市公园为对象，按照社交媒体平台优先推荐植物观赏类城市公园
的原则筛选，挖掘并解译用户生成数据，借助自然语言处理算法揭示公众对园林植物的感知偏好特征及影响因素。研究表明，公众对植物的感知主要集中在植物
种类、季相和植物印象3个方面。其中植物种类感知与季相、感官呈显著正相关，与公园情感得分呈负相关。平台推荐引导的植物感知重点和公众评论中的实际感
知基本一致。最后，依据分析结果提出公园季相、观赏错峰、观赏种类创新、观赏植物科教4个方面的植物景观优化建议，为城市公园的园林植物配置优化、公众
感知友好型城市公园规划设计等提供研究实证参考。 |
| 关键词: 园林植物 风景园林 城市公园 用户生成数据 自然语言处理 景观感知 |
| DOI：10.19775/j.cla.2025.01.0125 |
| 投稿时间：2023-09-13修订日期：2024-04-18 |
| 基金项目:国家自然科学基金项目(52408063，52208083)；湖北省自然科学基金项目(2023AFB139)；中央高校基本科研业务费专项资金(2042024kf0029) |
|
| Research on Perceived Preferences for Garden Plants Based on User-Generated Data and NaturalLanguage Processing: A Case Study of Urban Parks in Wuhan |
| SU Chang,CHEN Yixiu,,YIN Lihua,,GUO Shiyi* |
| Abstract: |
| Rapid urbanization has led to mental health problems among residents,
and urban green spaces can alleviate these problems, with landscape plants
playing a crucial role. Previous studies have mostly been confined to specific plant
species or perceptual characteristics and have seldom been carried out from the
public's perspective in combination with user-generated data. With the widespread
popularization of the Internet, user-generated data and natural language processing
methods have provided new avenues for related research. Given the rapid
development of urbanization in Wuhan and the diverse types of parks, taking urban
parks in Wuhan as the object, this study mined user-generated data and employed
natural language processing algorithms to disclose the perceptual preference
characteristics and influencing factors of landscape plants, which provides
references for the optimization of plant configuration in urban parks. A total of 11
urban parks with high recommendation popularity on Xiaohongshu were selected
as research objects, and ornamental recommended plants were extracted according
to the recommendation content. The review data about parks were collected
from Ctrip and then processed using natural language processing and analysis
methods. The jieba library was used to count high-frequency words, and perceptual
characteristic categories were established with reference to previous studies. Highfrequency
words were expanded using word vectors to construct a perceptual
dictionary. Reviews were segmented, and perceptual frequencies and proportions
were calculated. The paddle NLP library was used to conduct sentiment analysis on
reviews to obtain the comprehensive sentiment score of the parks. The characteristics
of plant perception in the reviews are presented as follows: 1) Analysis of high-frequency
characteristic words related to plants: Among the top 300 high-frequency words,
plant-related words accounted for 5.7%. The "plant species" category appeared
most frequently, and "cherry blossom" had the highest word frequency. Compared
with the recommended words on Xiaohongshu, most high-frequency plants were mentioned,
but some words only appeared on Xiaohongshu. 2) Correlations between the perception
of landscape plants and the results of emotional analysis: Among all the reviews,
plant-related words accounted for 6.87%, and the "plant species" had the highest
public perception frequency. "Plant species" was significantly positively correlated
with "plant season" and "sensory perception" but significantly negatively correlated
with the park sentiment score; "plant impression" was positively correlated with the
number of recommendations on Xiaohongshu; "plant science popularization" and
"emotional experience" was not significantly correlated with other categories. The
research results showed that: 1) The public's perceptual preference characteristics
of landscape plants: The public's perception of plants was mainly focused on
"plant impression", "plant species", and "plant season". The perception of "plant
species" was negatively correlated with the park sentiment score, possibly because
popular plants have short flowering periods and are easily missed, and the offseason
landscape is poor, which can easily lead to negative emotions. 2) The
perceptual preference characteristics of landscape plants in different park types: The
proportion of plant perception and the perception of plant species were prominent
in plant specialty parks. There were large differences in perception among
comprehensive parks, and the comfort perception in urban wetland and forest
parks was high. Through cluster analysis, parks were divided into four groups with
different perceptual characteristics. 3) Optimization suggestions for garden plant
configuration based on public perception: It is of great importance to make up for the
differences in park phenology, stagger the viewing periods of characteristic plants,
innovate the types of ornamental plants, and strengthen plant science education.
This study reveals the public's perceptual preference for garden plants and the
perceptual characteristics for different park types, and puts forward optimization
suggestions, providing empirical research references for the optimization of garden
plant configuration in urban parks and the planning and design of public perceptionfriendly
urban parks. However, the study has certain limitations, such as limitations
in data interpretation methods and diversity, differences between public perception
data and actual visitors, and failure to discuss the perception influence mechanism.
In the future, combined with image data calibration, a comprehensive perception
system will be constructed, park spatial characteristic indicators will be quantified,
and the research scope will be expanded. |
| Key words: landscape plants landscape architecture urban parks user-generated
data natural language processing landscape perception |
