Research on Rural Tourism Feature Segmentation Method Based on
Hierarchical Cluster Analysis
Wu Jun
Wuhan Railway Vocational College of Technology, 430205, China
Keywords: Chain Link Theory, Hierarchical Clustering, Characterization Method, Rural, Tourism Features.
Abstract: The feature division method plays an important role in rural tourism, but there is the problem of inaccurate
division and positioning. The traditional deep learning algorithm cannot solve the problem of dividing
characteristics in rural tourism, and the effect is not satisfactory. With the continuous development of modern
tourism, people's demand for tourism is gradually diversified and personalized. In particular, rural tourism,
with its unique natural scenery, traditional culture and pastoral life experience, has become the first choice
for more and more urban residents for leisure and vacation. However, due to the diversity and complexity of
resources in rural areas, how to scientifically and effectively develop and manage tourism resources and
enhance the attractiveness and competitiveness of rural tourism has become the focus of attention in the
industry. In this context, hierarchical cluster analysis, as an effective data mining technique, provides a new
perspective and method for the characteristic division of rural tourism..
1 INTRODUCTION
The so-called hierarchical clustering analysis refers to
the construction of a hierarchical structure of data to
gather objects with high similarity together to form
different categories or groups (Liu and Ai, et al.
2022). This method does not rely on pre-set
classification criteria, and can reveal the internal
structure and laws of the data based on its own
characteristics (Zhang and He, et al. 2022). In the
classification of rural tourism characteristics,
hierarchical cluster analysis can help us identify the
types of tourism resources in different rural areas, so
as to formulate more accurate and efficient
development strategies (Zheng, 2022).
2 RELATED CONCEPTS
2.1 Mathematical Description of
Hierarchical Clustering Analysis
First of all, through the detailed investigation and data
collection of rural tourism resources, including
natural landscapes, cultural heritage, folk activities,
characteristic industries and other dimensions (Ding,
and Zhou, et al. 2022), we can build a comprehensive
database of rural tourism resources.
()
!
lim( ) max(
2
!!
iij ij ij
x
n
yt y t
rnr
→∞
⋅= ≥ ÷
−
(1
)
Among them, the judgment of outliers is shown in
Equation (2).
2
max( ) ( 2 ) ( 4)
ij ij ij ij
tttmeant=Χ + ⋅ +
M
(2
)
Next, the hierarchical clustering analysis is used
to process these data to find which resources have
strong correlations with each other and which are
relatively independent (Chen and Sun, et al. 2023).
The results of this analysis help us to identify the
characteristic resources of each rural area, and then
determine the direction and focus of its tourism
development (Sun and Wang, et al. 2023).
For example, for those rural areas that are
dominated by natural scenery, we can discover the
distribution and characteristics of their main natural
attractions through cluster analysis, and then build
ecotourism products around these core resources (JI
and PEI, 2022). For villages rich in cultural and
historical resources, their unique historical and
cultural context can be discovered through clustering,
182
Jun, W.
Research on Rural Tourism Feature Segmentation Method Based on Hierarchical Cluster Analysis.
DOI: 10.5220/0013538000004664
Paper published under CC license (CC BY-NC-ND 4.0)
In Proceedings of the 3rd International Conference on Futuristic Technology (INCOFT 2025) - Volume 1, pages 182-187
ISBN: 978-989-758-763-4
Proceedings Copyright © 2025 by SCITEPRESS – Science and Technology Publications, Lda.
and cultural tourism projects can be carried out
accordingly.
2
() 4 2
ii
Fd b ac t
y
ξ
=− ⋅→
(3)
2.2 Selection of Feature Division
Method Scheme
For villages featuring agriculture and handicrafts,
cluster analysis can help us understand the current
situation and potential of industrial development, and
promote the combined development of industrial
tourism (Tang and Sha, 2022).
()= ( )
ii i i
dy
gt x z Fd w
dx
⋅−
∏
(4)
In addition, hierarchical cluster analysis can also
be used for rural tourism market segmentation.
Through the analysis of tourists' behavior patterns,
consumption habits and other data, tourists can be
divided into different groups, such as parent-child
families, backpackers, photography enthusiasts, etc.
2
lim ( ) ( ) 4 max( )
ii ij
x
gt Fd b ac t
→∞
+≤−
(5
)
And then provide customized tourism services
and products according to the characteristics and
needs of different groups, so as to improve the
satisfaction and loyalty of tourists.
() ( ) ( 4)
ii ij
gt Fd mean t+↔ +
(6
)
2.3 Analysis of the Scheme of the
Feature Division Method
In conclusion, hierarchical cluster analysis, as a
powerful data analysis tool, shows great potential in
the classification of rural tourism characteristics. It
can not only help us better understand and grasp the
diversity of rural tourism resources, but also guide us
to carry out more targeted tourism planning and
management, and ultimately realize the sustainable
development of rural tourism (Dai and Xu, et al.
2022). With the continuous progress of big data
technology and artificial intelligence, we have reason
to believe that hierarchical cluster analysis will play a
more important role in the field of rural tourism and
contribute wisdom and strength to the
implementation of rural revitalization strategy.
() ( )
()
(4)
ii
i
ij
gt Fd
No t
mean t
+
=Β
+
(7
)
Hierarchical clustering is an exploratory data
analysis tool that shows the aggregation process
between data points in the form of a dendrogram by
constructing a multi-level nested cluster structure.
() [ () ( )]
iii
Z
ht gt F d=+
(8
)
With the growth of modern tourism consumers'
demand for personalized and experiential tourism,
rural tourism has become a new choice for more and
more tourists with its unique natural scenery,
traditional culture and local characteristics. However,
in the face of many rural destinations with different
characteristics, how to accurately capture and divide
their unique characteristics, so as to provide tourists
with more accurate travel recommendations? At this
time, an effective multivariate statistical analysis
method, Hierarchical Cluster Analysis (HCA), shows
its important value.
min[ ( ) ( )]
( ) 100%
() ( )
ii
i
ii
gt Fd
accur t
gt Fd
+
=×
+
(9
)
In rural tourism studies, HCA was able to classify
rural destinations with similar characteristics into the
same cluster based on a series of key indicators, while
those with high dissimilarities remained
independently classified. These indicators may
include multi-dimensional information such as
geographical location, natural environment, cultural
background, tourism facilities, activities, local
specialties, etc.
min[ ( ) ( )]
()
() ( )
ii
i
ii
gt Fd
accur t
gt Fd
+
=Γ
+
(10
)
For example, if a region is known for its rich
intangible cultural heritage, such as traditional crafts
or festivals, they may form a cluster with cultural
characteristics at its core, or villages may be grouped
together because they have similar pastoral
landscapes and agricultural experiences, which can
help attract tourists who are interested in rural life.
Research on Rural Tourism Feature Segmentation Method Based on Hierarchical Cluster Analysis
183
3 OPTIMIZATION STRATEGY
OF FEATURE DIVISION
METHOD
The application of hierarchical cluster analysis in the
study of rural tourism can not only help managers
identify the unique selling points and development
potential of each rural tourism destination, but also
promote the rational planning and integration of
regional tourism resources. For example, through the
analysis of the data, local governments can carry out
targeted brand building and formulate differentiated
marketing strategies, so as to improve the
competitiveness and attractiveness of rural tourism
destinations.
3.1 Introduction to the Feature
Division Method
In addition, from the perspective of travelers, the
results of hierarchical cluster analysis can be used as
a reference for them to choose destinations.
Table 1: Characteristics classification method requirements
Scope of
application
Grade Accuracy Feature
segmentation
metho
d
Geographical
environment
I 85.00 78.86
II 81.97 78.45
Cultural
herita
g
e
I 83.81 81.31
II 83.34 78.19
Ecology I 79.56 81.99
II 79.10 80.11
The process of the feature division method in
Table 1 is shown in Figure 1.
Feature division Analysis
Property
Hierarchical
clustering
Country
Chain link
Junketing
Figure 1: The analysis process of the feature division
method
In the fast-paced and stressful living environment
of modern society, more and more people are eager to
escape the hustle and bustle of the city and seek a
place of tranquility and nature. With its unique charm,
rural tourism has emerged as the times require, and
has become an excellent choice for urbanites to
release stress and find spiritual comfort. This article
will provide an in-depth analysis of what makes rural
tourism unique and how it has become a new trend in
modern tourism.
3.2 Characteristics Classification
Method
In summary, hierarchical cluster analysis, as a
powerful data processing method, has a non-
negligible role in interpreting the characteristics of
rural tourism. It not only provides decision-making
support for tourism managers, but also facilitates the
choice of tourists, and promotes the sustainable
development and diversification of rural tourism.
Therefore, the use of hierarchical cluster analysis to
dig deep into the intrinsic value and potential of rural
tourism has become an indispensable and important
part of today's tourism research and practice. Through
this scientific approach, we are able to capture the
uniqueness of rural tourism more accurately, and thus
contribute to the prosperity of tourism .
Table 2: The overall picture of the scheme of the
characterization method
Category Random
data
Reliability Analysis
rate
Geographical
environment
85.32 85.90 83.95
Cultural
herita
g
e
86.36 82.51 84.29
Ecology 84.16 84.92 83.68
Mean 86.84 84.85 84.40
X6 83.04 86.03 84.32
P=1.249
3.3 Feature Division Method and
Stability
By understanding the key features and benefits of
different clusters, travellers can more quickly identify
rural locations that match their travel preferences,
whether they are looking for tranquil natural scenery,
authentic village life, or historical and cultural traces.\
First of all, the most attractive feature of rural
tourism is the authentic and idyllic experience it
offers. Compared to traditional tourism, tourists can
participate in agricultural activities such as picking
INCOFT 2025 - International Conference on Futuristic Technology
184
fruits and vegetables, milking cows, and making local
delicacies.
Figure 2: Feature division methods of different algorithms
Table 3: Comparison of the accuracy of the feature division
methods of different methods
Algorithm Surve
y data
Feature
segmentati
on metho
d
Magnitu
de of
change
Erro
r
Hierarchic
al
clusterin
g
85.33 85.15 82.88 84.9
5
Deep
learning
algorithms
85.20 83.41 86.01 85.7
5
P 87.17 87.62 84.48 86.9
7
In addition, rural tourism also has strong
ecological advantages. Fresh air, pristine water and
rich biodiversity in rural areas provide visitors with a
natural retreat for wellness. Relaxing in such an
environment can effectively relieve the
environmental stresses of urban life and have a
positive impact on physical health.
Figure 3: Characterization methods for hierarchical
clustering
In addition, many traditional customs and
handicrafts are often preserved in rural areas, which
are valuable cultural heritage that is hard to find in the
process of urbanization. Through rural tourism,
visitors have the opportunity to observe and even
learn ancient skills such as pottery, weaving, and
carpentry up close, which not only enriches their
travel experience, but also helps to pass on and
preserve these fading traditional skills.
3.4 Rationality of the Feature Division
Method
This sense of participation and experientiality is
unique to rural tourism, which allows visitors to
change from passive sightseeing to active
participation, so as to gain a deeper cultural
experience and a sense of personal fulfillment.
Figure 4: Feature division methods of different algorithms
It is worth mentioning that as the concept of
sustainable development is deeply rooted in the hearts
of the people, rural tourism plays an important role in
promoting local economic development. By
encouraging tourists to participate in the local
economic life, such as buying farm products and
staying in homestays, it not only increases the income
of rural households, but also promotes the diversified
development of the rural economy.
3.5 The Effectiveness of the Feature
Segmentation Method
Finally, the low-density nature of rural tourism is also
an attractive factor. Compared to the crowds of
popular tourist attractions, rural tourism offers a more
private and tranquil way to travel. This spatial
freedom and tranquility allows visitors to better enjoy
their journey and truly relax physically and mentally.
Research on Rural Tourism Feature Segmentation Method Based on Hierarchical Cluster Analysis
185
Figure 5: Feature division methods of different algorithms
Undoubtedly, as an important branch of modern
tourism, it will continue to be welcomed and sought
after by more and more people, and become a green
haven for urbanites to return to nature.
Table 4: Comparison of the effectiveness of different
methods
Algorithm Surve
y data
Feature
segmentati
on metho
d
Magnitu
de of
change
Erro
r
Hierarchic
al
Clusterin
g
82.21 85.92 84.59 82.8
5
Deep
learning
algorithms
83.73 84.23 84.41 83.5
5
P 84.20 87.39 84.76 83.9
0
It can be seen from Table 4 that the deep learning
algorithm has shortcomings in the accuracy of the
feature division method, and the feature division
method changes greatly, and the error rate is high.
The feature division method of the general results of
hierarchical clustering analysis is higher than that of
deep learning algorithms. At the same time, the
feature division method of hierarchical clustering
analysis is greater than 90%, and the accuracy does
not change significantly. To further verify the
superiority of hierarchical clustering. In order to
further verify the effectiveness of the proposed
method in this paper, the general analysis of
hierarchical clustering analysis is performed with
different methods, Figure 6 shown.
Figure 6: Hierarchical clustering analysis feature division
method
It can be seen from Figure 6. that the feature
division method of hierarchical cluster analysis is
significantly better than the deep learning algorithm,
and the reason is that hierarchical cluster analysis
increases the adjustment coefficient of feature
division method and sets the threshold of Internet
information to eliminate the feature division method
scheme that does not meet the requirements.
4 CONCLUSIONS
All in all, rural tourism is not just a simple form of
tourism, it is a bridge between the city and the
countryside, and a dream place for modern people to
live in harmony with nature. By providing an
authentic rural experience, preserving traditional
cultures, promoting ecological sustainability, and
supporting local economies, rural tourism has
demonstrated its unique and far-reaching appeal.
REFERENCES
Liu Kangming, Ai Ge, Zhang Yu, & Fu Yu. (2022).
Research on BTS clustering algorithm based on
hierarchical clustering and segmentation clustering
algorithm. Network Security Technology and
Application(005), 000.
Chunlin Zhang, Fei He, Zhe Li, & Junjun He. (2022).
Classification of sauce-flavored liquor base wine based
on principal component analysis and hierarchical
cluster analysis. China Brewing(008), 041.
ZHENG Zhuyu. (2022). Research on the refinement and
regional reproduction of rural landscape characteristics
INCOFT 2025 - International Conference on Futuristic Technology
186
in eastern Yudong. (Doctoral dissertation, Zhengzhou
University of Light Industry).
Ding Jieping, Zhou Jing, Zhang Yaqun, & Shang Tingting.
(2022). Water quality evaluation of Lanzhou section of
Yellow River based on hierarchical cluster analysis and
water quality labeling index. Environmental Ecology,
4(5), 6.
Chen Mo, Sun Lei, Wang Yuhui, Zhou Tongle, & Liu
Jiamin. (2023). Prediction method of air combat target
intention game based on nearest neighbor hierarchical
clustering analysis. CN115719112A.
Sun Wenjie, Wang Donghong, Zhao Ruihua, Yu Yiwei,
Yang Yanhuan, & Shi et al. (2023). Discussion on TCM
syndrome of benign female breast nodules based on
clustering and factor analysis. Chinese Journal of
Traditional Chinese Medicine Information.
JI Jiangshuai, PEI Songwen. (2022). Research on intelligent
hierarchical clustering algorithm for heterogeneous
genetic data. Journal of Chinese Computer Systems,
43(9), 1808-1813.
Tang Miaojia, & Sha Jian. (2022). Research on tobacco
illegal zoning based on hierarchical clustering
algorithm. Electronic Technology and Software
Engineering(012), 000.
Dai Xianyong, Xu Xiong, Deng Jinxiang, Yu Xiangji,
Xiong Zhu, Xiong Min. (2022). Multi-strategy
unknown protocol classification method based on
hierarchical clustering. Information Security and
Communication Confidentiality (3), 88-100.
Research on Rural Tourism Feature Segmentation Method Based on Hierarchical Cluster Analysis
187
