Research on Image Perception Measurement of Air Tourism Based
on Network Text Mining
Xing Lei
1
and Xu Xiaxin
2
1
Hainan Technology and Business College, Haikou, Hainan Province 570203, China
2
Hainan Cometour Business Tavel Service Co., Ltd, 570100, China
Keywords: Natural Language Processing Theory, Network Text Mining, Perceptual Measure Studies, Aviation, Tourism,
Image.
Abstract: Perceptual measurement research plays an important role in the image of air tourism, but there is a problem
of inaccurate perception. The traditional data mining algorithm cannot solve the measurement perception
problem in the image of air tourism, and the effect is not satisfactory. In the wave of informatization, the
tourism industry is ushering in unprecedented changes. As an important part of air tourism, its image
perception directly affects consumers' choice and satisfaction. How to accurately grasp this image has become
the focus of attention in the industry. As an important tool for big data analysis, online text mining is gradually
revealing its great potential in this field.
1 INTRODUCTION
Web text mining refers to the process of extracting
valuable information and knowledge from a large
number of web texts through computer technology. In
the field of air travel (Zhang and Xue, et al. 2020),
this means that the public's perception of different
airlines and their services can be understood by
analyzing online reviews, social media posts, blog
posts, and more (Wang and Ye, et al. 2021). This
collection of perceptions constitutes the public's
image perception of air tourism (Ao and Li, et al.
2020).
2 RELATED CONCEPTS
2.1 Mathematical Description of
Network Text Mining
By digging deeper into this textual data, we can not
only identify consumers' general perceptions of
aviation services, but also uncover trends and patterns
hidden behind the data (Wang and Wang, 2018). For
example, an airline may be considered to have a high
quality of service because it frequently appears in
positive reviews, while another company may be
flagged for improvement because of the constant flow
of negative information.
lim( ) max( 2)
iij ij ij
x
yt y t
→∞
⋅=≥ ÷
(1
)
Among them, the judgment of outliers is shown in
Equation (2).
2
max( ) ( 2 ) ( 4)
ij ij ij ij
tttmeant=∂ + ⋅ +

 M
(2
)
Therefore, for practitioners in the travel industry,
embracing online text mining is embracing a valuable
opportunity to gain insight into consumer
psychology, optimize service experience, and stay
ahead in the fierce market competition (Zhang and
Xue, et al. 2020).
() 2 7
ii i
Fd t y ξ =⋅→⋅

∏




(3
)
2.2 Selection of Perceptual Measure
Study Protocols
Hypothesis II The perceptual measure study function
is
()
i
gt
, and the weight coefficient is
i
w
, then the
Lei, X. and Xiaxin, X.
Research on Image Perception Measurement of Air Tourism Based on Network Text Mining.
DOI: 10.5220/0013545200004664
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 441-446
ISBN: 978-989-758-763-4
Proceedings Copyright © 2025 by SCITEPRESS – Science and Technology Publications, Lda.
441

perceptual measure study requires the unqualified
perceptual measure study as shown in Equation (4).
()= ( )
ii i i
dy
gt x z Fd w
dx
⋅−
∏

(4)
For example, if data shows that consumer interest
in a destination is increasing, airlines can increase the
number of flights to that destination (Wang and Lin,
et al. 2021). Similarly, if a certain type of complaint
starts to rise, companies can quickly take steps to
resolve the issue to avoid reputational damage.
lim ( ) ( ) max( )
ii ij
x
gt Fd t
→∞
+≤

(5)
To improve the effectiveness of perceptual
measure studies, all data needs to be standardized and
the results is shown in Equation (6).

() ( ) ( 4)
ii ij
gt Fd mean t+↔ +

(6
)
2.3 Analysis of perceptual measure
study protocols
The advantage of online text mining is its ability to
process massive amounts of data and to continuously
monitor changes in public sentiment. This is crucial
for air travel companies, as they can adjust their
strategies in real-time in response to market changes
(Zhang and Wang, 2015).

2
() ( )
() 4
(4)
ii
i
ij
gt Fd
No t b ac
mean t
+
=−
+

(7
)
Among them, it is

() ( )
1
(4)
ii
ij
gt Fd
mean t
+
≤
+

stated
that the scheme needs to be proposed, otherwise the
scheme integration is
()
i
Z
ht
required, and the result
is shown in Equation (8).

() [ () ( )]
iii
Z
ht gt F d=+

(8)
However, web text mining is not a panacea. Its
accuracy and validity depend on a variety of factors,
including the quality of the data, the choice of
analytical method, and the ability to interpret the
results (Shan and Wang, et al. 2019). Therefore, while
online text mining provides us with a powerful tool
for understanding air travel image perception, it also
needs to be combined with other market research
methods to ensure that the conclusions drawn are
comprehensive and reliable (Yang, 2021).


min[ ( ) ( )]
( ) 100%
() ( )
ii
i
ii
gt Fd
accur t
gt Fd
+
=×
+


(9
)
In addition, web text mining can also be used to
predict market trends. By analyzing past data and
building models, it is possible to predict possible
changes in consumer behavior in the future (Zhi and
Wang, et al. 2023). This is essential for air travel
companies to stay ahead of the curve in a competitive
market.


min[ ( ) ( )]
() ()
() ( )
ii
ii
ii
gt Fd
accur t randon t
gt Fd
+
=+
+


(10
)
Today, with the rapid development of information
technology, the competition in the tourism industry is
not only limited to the quality of service and the
uniqueness of scenic spots (Kang and Xie, et al.
2023). How to shape and maintain a positive and
attractive tourism destination image in the sea of
information has become a challenge that local
governments and tourism boards must face.
3 OPTIMIZATION STRATEGIES
FOR PERCEPTUAL MEASURE
STUDIES
In conclusion, online text mining provides a unique
perspective for the air travel industry, allowing it to
better understand and shape the public's image
perception of air tourism. With the continuous
advancement of technology and the increasing
maturity of data analysis methods, we have reason to
believe that online text mining will play an
increasingly important role in the future of air travel
market research. For air travel companies, mastering
this technology means holding the key to winning the
market.
INCOFT 2025 - International Conference on Futuristic Technology
442

3.1 Introduction to Perceptual
Measure Research
At this time, online text mining technology came into
being, which has become an important tool to
measure and analyze the public's perception of the
image of a specific tourist destination.
Table 1: Perceptual measurement study requirements
Scope of
application
Grade Accuracy Perceptual
measure
studies
Airline I 85.00 78.86
II 81.97 78.45
Tourism
agencies
I 83.81 81.31
II 83.34 78.19
Government
agencies
I 79.56 81.99
II 79.10 80.11
The perceptual measure study process in Table 1.
is shown in Figure 1.
Network text Analysis
Visualize
Natural language
Perception
measure
Navigate Tour
Figure 1: The analytical process of perceptual measure
studies
Web text mining, in short, is the process of
extracting useful information from a large amount of
online text materials using computer programming
techniques. This includes social media posts, blog
posts, comments, and forum discussions, among
others. By analyzing these texts quantitatively and
qualitatively, researchers can gain insight into the real
experience of visitors and understand what factors
influence their satisfaction and willingness to return
to visit.
3.2 Perceptual Measurement Research
For example, sentiment analysis can be used to
determine the overall sentiment of visitors about their
accommodation from hotel reviews, and topic
modeling can be used to identify the most discussed
attractions or service issues among tourists. In
addition, keyword frequency analysis helps us
understand which featured words or phrases are
closely associated with a particular travel destination,
and in turn, evaluate the visibility and attractiveness
of the destination's brand image.
Table 2: Perceptual measures study protocol as a whole
Category Random
data
Reliability Analysis
rate
Airline 85.32 85.90 83.95
Tourism
agencies
86.36 82.51 84.29
Government
agencies
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 Perceptual Measure Studies and
Stability
But the applications of text mining on the web are
much more than that. It is also able to predict travel
trends and provide data support for marketing. For
example, by tracking how much discussion a
destination is on the web, it is possible to predict
future visitor flows.
Figure 2: Study on perception measurement of different
algorithms
Looking to the future, with the continuous
advancement of artificial intelligence and machine
learning technology, online text mining will play an
increasingly important role in the field of tourism
image perception measurement. This not only helps
destination managers better understand and shape
their brand image, but also provides a richer and more
Research on Image Perception Measurement of Air Tourism Based on Network Text Mining
443

authentic source of information for potential
travelers. Eventually, network text mining will
promote the development of tourism in a more
personalized and intelligent direction, and realize the
effective allocation of resources and the accurate
docking of the market.
Table 3: Comparison of perceptual measures of study
accuracy by different methods
Algorithm Surve
y data
Perceptua
l measure
studies
Magnitud
e of
change
Error
Network
text
mining
85.33 85.15 82.88 84.9
5
Data
mining
algorithm
s
85.20 83.41 86.01 85.7
5
P 87.17 87.62 84.48 86.9
7
It's worth mentioning that web text mining is not
without its challenges. The sheer volume and
diversity of data brings with it the problem of noise
and inaccurate information. At the same time, the
limitations of natural language processing technology
can also lead to misunderstandings of tourists' true
intentions. Therefore, a combination of accurate data
cleaning, efficient algorithm design, and manual
verification is the key to ensure the accuracy of the
results.
Figure 3: Research on perceptual measurement of network
text mining
Network data is as vast and deep as an ocean.
There is tremendous value in this data, especially for
the travel industry, where understanding and
analysing tourists' online comments, discussions, and
behaviour patterns has become an important means of
understanding the image and perception of tourism.
And online text mining technology is the key to
unlocking this treasure trove of data.
3.4 The Rationality of Perceptual
Measure Studies
At the same time, combined with time series analysis
and geotagging data, we can also observe how
specific holidays or seasonal events affect visitors'
perception of the place.
In short, as an emerging data analysis method,
online text mining is gradually changing our
understanding and evaluation methods of tourist
destination image. It not only provides us with a new
perspective to observe and measure public
perception, but also opens up new ways to optimize
and enhance the brand impact of tourism destinations.
With the in-depth application of this technology, the
construction of tourism image in the future will be
more scientific and data-driven, so as to better meet
the needs of tourists and promote the sustainable
prosperity of the global tourism industry.
Figure 4: Perceptual measures of different algorithms
3.5 Effectiveness of Perceptual
Measure Studies
Web Text Mining refers to the process of using data
mining techniques and algorithms to discover
valuable information from text on the Internet. In the
travel sector, this means that the vast amount of user-
generated content (UGC) from social media, blogs,
forums and review sites can be systematically
analysed to get real feedback about a destination or
service.
INCOFT 2025 - International Conference on Futuristic Technology
444

Figure 5: Perceptual measures of different algorithms
Imagine that by analyzing the reviews of a tourist
destination on the Internet, we can clearly see how
satisfied tourists are with the environment, culture,
facilities, etc., and even find out which factors are
most important to them. This is not only an
affirmation or denial of existing services, but also a
guide for future development. For example, if the
majority of visitors are unhappy with the congestion
level of a tourist attraction, the administrator may be
justified in adjusting crowd control measures to
improve the overall visitor experience.
Table 4: Comparison of the effectiveness of perceptual
measures of different methods
Algorithm Surve
y data
Perceptua
l measure
studies
Magnitud
e of
chan
g
e
Error
Network
text
minin
g
82.21 85.92 84.59 82.8
5
Data
mining
algorithm
s
83.73 84.23 84.41 83.5
5
P 84.20 87.39 84.76 83.9
0
In addition, the topic model is also an
indispensable tool in online text mining. It helps us
identify themes and keywords that recur in many
texts, providing travel planners with valuable
information about current popular travel activities,
common concerns among travelers, and even
predicting trends that may emerge in the future.
Figure 6: Research on Perceptual Measures of Network
Text Mining
Another powerful aspect of web text mining lies
in sentiment analysis. By judging the sentimental
tendencies of online reviews, we can not only
quantify the proportion of positive and negative
reviews, but also track the trend of sentiment over
time, which is essential for evaluating the
effectiveness of marketing campaigns or monitoring
the response to crisis events.
4 CONCLUSIONS
Of course, web text mining is not without its
challenges. The sheer volume and diversity of data
requires sophisticated algorithms to clean, classify,
and parse text, and to obtain accurate and reliable
results, models need to be continuously optimized to
adapt to changing web languages and expressions.
Online text mining provides us with a new
perspective to observe and understand the image of
tourism and the perception of tourists. It not only
helps us capture details that were difficult to reach
with traditional survey methods in the past, but also
responds to changes in the market and consumers in
real time. In the future, with the continuous progress
and innovation of technology, online text mining will
play an increasingly important role in tourism image
shaping and management.
REFERENCES
Zhang Yang, Jin Xue, & Gong Xianjie. (2020). Research
on the Perception Measurement of General Aviation
Tourism Image in Shaanxi Based on Network Text
Research on Image Perception Measurement of Air Tourism Based on Network Text Mining
445

Mining. Journal of Xi'an Shiyou University: Social
Sciences Edition, 29(3), 6.
Wang Fang, Ye Lin, Sun Hao. (2021). Research on
Perceived Image of Urban Tourism Based on Network
Text Data Mining: A Case Study of Hefei City. Journal
of Changzhou Institute of Technology, 34(3), 73-79.
Ao Changlin, Li Fengjiao, Xu Lishan, & Sun Baosheng.
(2020). Research on Perception of Ice and Snow
Tourism Image Based on Network Text Mining: A
Case Study of Harbin City. Mathematics in Practice and
Understanding (1), 11.
Wang Haoyu, & Wang Qiang. (2018). Research on Tourist
Image Perception and Preference Based on Network
Travelogue Text Mining: A Case Study of Hainan
Province. Contemporary Tourism (11), 3.
Zhang Yang, Jin Xue, & Gong Xianjie. (2020). Research
on Dimensional Differentiation of Tourism Image in
Aviation Town Based on Network Text Analysis.
Henan Science, 38(5), 7.
Wang Fang, Ye Lin, & Sun Hao. (2021). Research on
Perceived Image of Urban Tourism Based on Network
Text Data Mining: A Case Study of Hefei City.
Zhang Hui, Wang Bing. (2015). Measurement and
Comparison of Government Public Value Based on
Text Mining. Journal of Anhui University of Science
and Technology (Social Sciences Edition), 017(001),
35-39.
Shan Mengyu, Wang Lu, & An Xinxin. Research on the
Perception of "Internet Celebrity" Tourism Destination
Image Based on Network Text Analysis. 2019 Southern
Expo Academic Symposium.
Yang Yakun. (2021). Research on Clustering Algorithms
Based on Web Text Mining. (Doctoral dissertation,
Inner Mongolia University of Science and
Technology).
Zhi Haocong, Wang Xiaohang, Li Shunbin, Deng
Qingwen, Sun Tianning, & Wan Zhiquan, et al. (2023).
A Traffic-Awis Topology Reconstruction Method in
Multi-Chip Grain Interconnect Network.
CN116260760A.
Kang Qiuhua, Xie Lichao, & Cai Yuanhong. (2023). A
Novel Network Server Based on Intelligent Perception.
INCOFT 2025 - International Conference on Futuristic Technology
446