Tourism destination marketing strategy driven by big data

Abstract

In this study, the marketing strategy of tourism destination driven by big data is deeply discussed. Firstly, the application of big data in the tourism industry and the current strategy of tourism destination marketing are analyzed, and then the research methods are designed through factor analysis and big data analysis theory. After processing and factor analysis of the collected data, the influence of big data on tourism destination marketing strategy is analyzed, and the possible optimization path is explored. At the same time, the problems and challenges encountered in this process are also found and analyzed. Based on these analysis results, this study provides some theoretical and practical implications to promote the application of big data in tourism destination marketing strategies. Finally, it emphasizes the importance of big data and factor analysis in the formulation of future tourism destination marketing strategy, and puts forward the direction of future research.

Keywords

Big data tourist destination marketing strategy factor analysis data analysis

1. Introduction

In the era of globalization and rapid development of information, tourism has become one of the important pillars of the world economy. Tourism destination marketing is particularly important in this context. It not only helps to improve the visibility of the destination, attract more tourists, but also enhances the competitiveness of the destination and drives the development of local economy. Tourism destination marketing refers to the comprehensive and in-depth development and utilization of tourism destination resources, through effective marketing strategies to convey the image of the destination to potential tourists, attract and promote them to choose specific tourism destinations. In the current tourism market, the application of big data provides a new impetus and perspective for tourism destination marketing. Big data technology is capable of processing and analyzing vast amounts of travel-related data, such as tourist behavior, preferences and market trends, to provide more precise insights into destination marketing. This data-driven approach can help tourism destinations identify their target markets more effectively and tailor personalized marketing strategies to enhance the attractiveness and competitiveness of the destination. For example, some well-known tourism destinations use big data to analyze visitors’ online behavior and feedback to optimize their website content and online marketing campaigns. By analyzing social media data, destinations can learn about visitors’ points of interest and discussions to design more engaging travel products and experiences. In addition, big data is also being applied to forecast tourism demand and market trends, enabling tourist destinations to better prepare for and respond to seasonal changes and market fluctuations. Through in-depth analysis of big data, tourism destinations can more accurately identify the needs of potential tourists and develop more effective marketing strategies. In addition, big data helps monitor and manage visitor flows to optimize visitor experiences and manage resources.

In recent years, with the development of big data technology, its application in the field of tourism destination marketing has received increasing attention. Duro et al. demonstrated the potential of big data in tourism sector analysis by using composite indexes to analyze the vulnerability of the tourism market [1]. In addition, Oender et al. demonstrated the importance of social media data in understanding tourism market trends by using Facebook data in tourism demand modeling and destination marketing [2]. In terms of tourism experience and visitor participation, Rather emphasized the importance of experiential marketing perspective in tourism destinations, which is closely related to in-depth understanding of tourist behavior in big data analysis [3]. The destination innovation matrix framework proposed by Gardiner and Scott provided new ideas for tourism experience and market development [4]. In addition, Bastiaansen et al. found that emotion measurement is of great value in tourism destination marketing by comparing brain waves and behavior [5]. Vodopivec and Ruzzier explored the marketing opportunities of wind sports tourism destinations through high-resolution wind analysis [6]. In terms of marketing strategy, Fjelldal et al. discussed the application of profanity in viral tourism marketing, providing a new perspective for destination image reinforcement [7]. Kilipiri et al. emphasized the importance of social media and influencer marketing by analyzing the role of Instagram in the promotion of sustainable tourism destinations [8]. Chang and Chiang showed that virtual reality technology, as a tool for tourism destination marketing, is effective from the perspective of fluid experience [9]. Ruiz-Meza et al. analyzed the impact of tourism planning and marketing strategies on destination brand equity through a system dynamics model [10]. In terms of practical application, Yin et al. studied the marketing power of short travel videos and emphasized the importance of enjoyment and authenticity [11]. Perkins et al. constructed a business cluster formation framework through participatory action research for marketing regional tourism destinations [12]. Current research shows that big data is playing an increasingly important role in tourism destination marketing.

The purpose of this study is to explore the application of big data in tourism destination marketing strategy and analyze its effect through factor analysis. The main purposes of this study are as follows: First, it is hoped to understand the practical application of big data in tourism destination marketing and reveal how big data affects the marketing effect of tourism destinations. Secondly, by using factor analysis method, we hope to deeply analyze the specific impact of big data on tourism destination marketing strategy and reveal the contribution of various factors to the tourism destination marketing effect. Finally, it is hoped that this study can provide data support and theoretical basis for tourism destinations to develop more effective marketing strategies, so as to enhance the competitiveness of tourism destinations.

The significance of this study is mainly reflected in the following aspects: On the one hand, for the academic circle, this study enriched the research on the application of big data in the tourism industry, provided a new perspective and method for the theoretical research on tourism marketing, and helped to promote the further development of tourism marketing theory. On the other hand, for the practical circle, this study provides a new analysis framework of tourism destination marketing strategies based on big data, which provides a basis for tourism destinations to develop more accurate and effective marketing strategies, and helps improve the market competitiveness of tourism destinations. All in all, this study has not only academic value, but also practical application value.

The main content of this study includes an overview of the application of big data in tourism destination marketing, an analysis of the existing tourism destination marketing strategies, and the application of factor analysis in tourism marketing research. Firstly, the literature is reviewed and a comprehensive understanding of these contents is obtained through in-depth analysis of the existing research. Big data analysis and factor analysis were used to ensure the accuracy and reliability of the results. Research methods are designed, then data is collected and processed, and the research objectives are achieved through factor analysis and big data analysis tools. In the research and implementation part, the method and process of data collection, data processing and factor analysis are introduced in detail. In addition, it also introduces the application of big data analysis tools and methods in tourism destination marketing strategy. In the section of data analysis and results, it shows the results of factor analysis and big data analysis, as well as the influence of these results on the tourism destination marketing strategy. The results are analyzed and the problems and challenges in the research are discussed. In the part of theoretical and practical enlightenment of tourism destination marketing strategy based on big data, the above analysis results are linked with the theory, so as to provide enlightenment for future research and practice. In the conclusion part, the whole study is summarized, highlighting the important findings of the study and the impact of these findings on the marketing strategies of tourism destinations.

The overall study is clearly structured and logically rigorous, aiming to provide an in-depth understanding of the application of big data in tourism destination marketing in order to drive further research in this field. The research process and ideas are shown in Fig. 1.

Figure 1.

Research process and ideas.

2. Status quo of tourism destination marketing and big data

2.1 Application status of big data in tourism marketing

The emergence of big data provides new possibilities and opportunities for tourism marketing. Modern tourism enterprises and destinations have begun to make deep use of big data to improve the effect of tourism marketing [13].

First, big data is widely used in market research and customer analysis of tourism destination marketing. By collecting and analyzing a large amount of customer data, including consumers’ personal information, travel history, online search and purchasing behavior, tourism companies and destinations can gain an in-depth understanding of consumers’ needs and preferences, and carry out accurate market positioning and product design.

Second, big data is also used to optimize the marketing strategies of tourist destinations. Through in-depth analysis of big data, tourism destinations can determine the most effective marketing channels, the best marketing time, the most suitable marketing information, etc., in order to improve the effect and return of marketing.

In addition, big data also plays an important role in the effectiveness evaluation of tourism destination marketing. Travel destinations can evaluate and optimize their marketing strategies by tracking and analyzing data generated by various marketing campaigns, such as click-through rates, conversion rates, customer feedback, etc.

However, although the application of big data in tourism marketing has a broad prospect, the current application level still has a lot of room for improvement. Some tourist destinations still face challenges in the application of big data, such as insufficient data collection and analysis capabilities, data security and privacy protection [14]. Therefore, how to make better use of big data to promote the development of tourism destination marketing is still a problem that needs further research and discussion.

2.2 Existing strategies of tourism destination marketing

In the tourism industry, the formulation and implementation of tourism destination marketing strategy is a key task, aiming at improving the attraction of tourism destinations and improving the economic benefits of tourism. The existing tourism destination marketing strategies mainly include the following aspects:

The comparison and analysis of the effect of tourism destination marketing strategy. Different strategies will have different effects on different target markets and destination characteristics. For example, social media marketing aimed at younger consumers may be more effective than traditional advertising, while customized travel experiences aimed at the high end of the market may be more revenue enhancing.

(1)
Target market selection and positioning: Tourism destinations need to clearly define their target market and understand the characteristics and needs of the target market, so as to conduct more accurate market positioning and product design.
(2)
Product development and optimization: According to the demand of the target market, tourism destinations need to develop and optimize tourism products, including tourist attractions, activities, services, etc., in order to provide tourism experience that meets the needs of consumers.
(3)
Price strategy: Price is an important factor affecting consumers’ purchase decisions. Tourism destinations need to formulate reasonable pricing strategies according to market conditions and consumer demand.
(4)
Promotion and publicity: through advertising, public relations activities, social media marketing, etc., to improve the visibility of the tourist destination and attract more tourists.
(5)
Cooperation and alliance: Through the formation of cooperation or alliance with other tourist destinations, travel agencies, airlines, etc., tourist destinations can expand their market influence and improve their market share.
(6)
Customer relationship management: By establishing and maintaining a good relationship with consumers, tourist destinations can improve consumer satisfaction and loyalty, and stabilize and expand tourist sources.

The applicability and effectiveness of these strategies vary in different market environments. For example, in a competitive market, innovative product development and unique promotion strategies may be more important; In mature markets, customer relationship management and pricing strategies can play a key role.

In the big data environment, the adaptability of the above-mentioned tourism destination marketing strategy is particularly critical. Big data provides a deeper and more accurate understanding of consumer demand and market changes, making the marketing strategy of tourist destinations more personalized and precise, and the marketing effect more significant. For example, big data analytics can help tourist destinations more accurately target markets, develop more effective pricing strategies, as well as optimize products and services to better meet consumer needs.

The acquisition process can be achieved in the following ways: To increase the attraction of destination resources mainly through market research, product innovation, and brand building; Providing customer service experiences focuses on customer feedback, service quality monitoring, and continuous service improvement.

Therefore, how to adjust and optimize tourism destination marketing strategy under the background of big data is an important direction of future tourism destination marketing research.
2.3 Application status of factor analysis method in tourism marketing research

Factor analysis is a statistical method mainly used to explore data health and structure to reveal the few key factors behind the large number of observed variables [15]. In tourism marketing research, factor analysis is widely used in the following aspects:

(1)
Analysis of tourism demand and preference: Through factor analysis of tourists’ behavioral data and satisfaction survey data, key factors affecting tourists’ demand and preference can be extracted, such as natural environment, cultural history and service quality of tourist destinations.
(2)
Market segmentation: Through factor analysis of tourists’ personal information, tourism behavior and consumption pattern, different market segments can be identified for more accurate market positioning and strategy formulation.
(3)
Marketing effect evaluation: Through factor analysis of the effect data of marketing activities, key factors affecting the marketing effect can be revealed, such as the content, form and release time of marketing information, so as to optimize the marketing strategy.

For example, in a study on a popular tourist city, researchers used factor analysis to extract key factors from tourists’ online evaluations, such as geographical location, cultural experience, and catering services, which had a significant impact on tourists’ overall satisfaction.

An in-depth discussion of the advantages and limitations of factor analysis in tourism data analysis, its advantage is that it can extract key information from a large number of complex data, which can help tourism destinations better understand tourist needs and market trends. However, the limitation of factor analysis is that it mainly reveals linear relationships, may not be able to capture nonlinear relationships and complex interaction effects, and has high requirements for data quality.

However, there are still some challenges in applying factor analysis method to tourism marketing research. First, there is the need to collect large amounts of high-quality data, which can be difficult in practice [16]. Secondly, the interpretation of factor analysis results requires professional knowledge and experience, which may be subjective. Finally, factor analysis can only reveal the linear relationship in the data, and may not fully capture the nonlinear relationship and complex interaction effect.

Therefore, although factor analysis is widely used in tourism marketing research, how to improve its application effect and make it better serve the formulation and optimization of tourism marketing strategy still needs further research. As shown in Fig. 2, factor analysis is widely used in tourism marketing research:

Figure 2.
Application status of factor analysis in tourism marketing research.

3. Theoretical framework and research methods

3.1 Big data analysis theory

Big data analysis is the process of conducting in-depth analysis based on large data sets to reveal the patterns, trends and associations hidden behind the data [17]. It is an integrated field involving several disciplines, including computer science, statistics, information systems, business intelligence and artificial intelligence. Big data analysis theory mainly includes the following key concepts:

(1)
Data collection and processing: This is the basic stage of big data analysis, including data collection from various sources, data cleaning, data conversion, data integration and other processing work to ensure the quality and applicability of data.
(2)
Data storage and management: In view of the characteristics of big data (such as large-scale, diversity, real-time, etc.), specific data storage and management tools, such as distributed file system and NoSQL database, are required.
(3)
Data analysis methods: Big data analysis mainly adopts statistical analysis, machine learning, data mining and other methods to extract useful information and knowledge from large-scale and complex data sets. Among them, machine learning and data mining methods are particularly important in the processing of unstructured data and predictive analysis.
(4)
Data visualization: Data visualization is to display the analysis results in a graphical way to help users understand and interpret data more intuitively and effectively. In big data analysis, data visualization is an essential part.

In tourism marketing research, big data analysis helps to deeply understand the needs and behaviors of consumers, optimize the marketing strategy of tourism destinations, and improve the marketing effect. Specifically, big data analytics can be used to analyze tourist behavior patterns, predict market trends, and evaluate the effectiveness of marketing campaigns. However, it also faces limitations, such as data security and privacy protection issues, data quality and credibility issues, and the complexity of interpretation and application of analytical results.

Examples can be given when discussing the application of big data analysis tools and methods. For example, use the Hadoop distributed file system to store and process large-scale data, utilize Apache Spark for efficient data processing and analysis, or use Google Analytics to analyze user behavior data on websites and social media. These tools and platforms enable researchers and marketers to analyze data more effectively to better understand and serve the travel market.
3.2 Factor analysis theory

Factor analysis is a statistical method mainly used to study the correlation between variables and to dig out the few potential factors or dimensions hidden behind a large number of observed variables [18]. The basic principle is that if there is a high correlation between a group of variables, then that group of variables may be driven by one or more shared underlying factors.

The following are the main steps of factor analysis:

(1)
Correlation matrix calculation: calculate the correlation matrix among all observed variables, which will be used for subsequent factor extraction.
(2)
Factor extraction: Potential factors are extracted by some method (such as principal component analysis or principal axis factor analysis) based on correlation matrix.
(3)
Factor rotation: The extracted factors are rotated (such as Varimax rotation or Promax rotation) to achieve better factor interpretation.
(4)
Factor score calculation: Factor score is calculated for each observation unit as the performance of the unit on each potential factor.

In tourism marketing research, factor analysis can help to understand the key factors affecting consumer choice and satisfaction, provide a basis for market segmentation and target market positioning, and provide theoretical support for the formulation and optimization of marketing strategies. However, factor analysis also has some limitations, such as high sample requirements, the result may be subjective, can not deal with the causal relationship between factors, etc., all these need to be paid attention to in practical application.
3.3 Research methods and design

This study will use quantitative research methods, including data collection, preprocessing, factor analysis and big data analysis. The following is the specific study design:

Data collection: The collection of data will mainly rely on user behavior data on travel websites and social media platforms, as well as relevant statistics from tourism agencies. This data might include users’ search history, ratings and reviews of travel destinations, users’ social networking behavior, etc.

Data preprocessing: After data collection, the research will conduct data preprocessing, including data cleaning, data conversion, data integration, etc., to ensure data quality and consistency.

Factor analysis: Factor analysis is carried out on the pre-processed data to reveal the key factors affecting destination choice and satisfaction. This step will be performed using the relevant statistical software.

Big data analysis: On the basis of factor analysis, big data analysis tools and methods (such as machine learning algorithms) are used to conduct in-depth analysis of data to identify the effect of tourism destination marketing and the influence of marketing strategies on tourism destination selection.

The design of this study aims to provide a new and scientific approach to support the formulation and optimization of tourism destination marketing strategies through the integrated application of factor analysis and big data analysis. Through this study, it is expected to provide valuable insights for practitioners of the tourism industry, and at the same time provide a new perspective and thinking for related theoretical research. The research methods and design are shown in Fig. 3.

Figure 3.

Research methods and design.

4. Research and implementation

4.1 Data collection methods and processes

In this study, multiple methods and channels will be used to collect data in order to construct a comprehensive and multivariate large data set.

(1)
Data collection method

Web crawler technology: Use web crawler technology to collect user behavior data from major travel websites and social media platforms. The data includes users’ search history, ratings and reviews of travel destinations, and users’ social networking behavior.

Tourism agency data: Apply to major tourism agencies for relevant statistical data, such as tourist destination visits, users’ booking records, users’ consumption records, etc.
(2)
Data collection process:

Identify the data sources: Identify the target websites and social media platforms for data collection, as well as the travel agencies with which the data is being collected.

Design and implement web crawler: Design and implement web crawler for target websites and platforms to collect user behavior data. In this process, the research will comply with relevant laws, regulations and ethics, and respect the privacy of users.

Apply for data from tourism agencies: Apply for relevant statistical data from tourism agencies, sign data use agreements, and ensure the legitimacy and security of data.

Data integration: Integrate all kinds of data collected into a unified data warehouse for data preprocessing.

Data quality control: In order to ensure data quality, the following measures will be taken in this study: In the data collection stage, the accuracy and relevance of data will be ensured by setting reasonable crawling rules and screening criteria. In the data preprocessing stage, the data will be cleaned and screened to eliminate invalid and duplicate data. Statistical analysis of the data is performed to assess the representativeness and reliability of the data.

Representativeness of the sample: To ensure the representativeness of the sample, this study will select multiple tourism websites and social media platforms of different regions and sizes for data collection, so as to cover different types of tourist groups. In addition, it will cooperate with a number of travel agencies to obtain user data in different markets and different consumption levels.

Assume that the collected data is $D=d_{1},d_{2},\ldots,d_{n}$ , where $n$ is the total number of data items, and $d_{i}$ represents the data item $i$ . Each piece of data $d_{i}$ includes several fields, such as user ID, travel destination, rating, review content, etc. For each tourist destination $t_{j}$ , its total visits $v_{j}$ and total score $s_{j}$ will be recorded to calculate its average score $\bar{s}_{j}=s_{j}/v_{j}$ .

The following table shows an example of some of the data collected.

Table 1
Data collection examples

User ID Tourist destination Score Comment content

1 A 4 “Beautiful scenery and good service.”

2 B 5 “I really like the culture here.”

3 A 3 “Transportation is not very convenient.”

$\ldots$ $\ldots$ $\ldots$ $\ldots$

4.2 Data processing and factor analysis

After collecting the original data, the research needs to preprocess the data, including data cleaning, data conversion and data standardization, in order to ensure the quality and consistency of the data. Then, factor analysis will be applied to analyze the processed data to reveal the key factors affecting destination choice and satisfaction.

Data processing process:

(1)
Data cleaning: remove incorrect or invalid data such as null value, duplicate value and outlier value. For example, if the user’s score is null or outside the score range (such as 1–5 points), this data is removed.
(2)
Data conversion: convert non-numerical data into numerical data. For example, the comment content is converted into emotion score through sentiment analysis, and the user’s search history is converted into visit frequency, etc.
(3)
Data standardization: data standardization to the same scale to eliminate the impact of data dimension. Commonly used methods include Z-score standardization, min-max standardization and so on.

Factor analysis:

Factor analysis is a statistical method used to explore the underlying factors behind a large number of variables. In this study, a factor analysis method will be used to reveal the key factors affecting destination choice and satisfaction.

Suppose you have $p$ a variable $X_{1},X_{2},\;ldots,X_{p}$ , research goal is to find potential factor $k\ F_{1},F_{2},\ldots,F_{k}$ ( $k<p)$ , such that each variable $X_{i}$ can be expressed as a linear combination of potential factors, as shown in Eq. (1):

$\displaystyle X_{i}=a_{i1}F_{1}+a_{i2}F_{2}+\ldots+a_{ik}F_{k}+e_{i}$ (1)

where $a_{ij}$ is the factor loading, according to the variable $X_{i}$ and factor, the relationship between $F_{j}$ , $e_{i}$ is a special factor, Represents the portion of $X_{i}$ that cannot be explained by common factors.

In this study, relevant statistical software will be used for factor analysis, including the steps of factor extraction, rotation and interpretation. Through factor analysis, it is expected to find a small group of independent potential factors to explain the main influencing factors of destination choice and satisfaction. These potential factors may include the natural environment, cultural atmosphere, service quality and transportation convenience of the tourist destination.

Table 2 shows some examples of processed data.

Table 2
Data processing and factor analysis examples

User ID Tourist destination Score Affective score Access frequency

1 A 4 0.8 5

2 B 5 0.9 3

3 A 3 0.6 2

$\ldots$ $\ldots$ $\ldots$ $\ldots$ $\ldots$

In this table, the sentiment score is obtained by sentiment analysis of the review content, and the frequency of visits is how often the user visits the travel destination.
4.3 Application of big data analysis tools and methods in tourism destination marketing strategies

In this study, big data analysis tools and methods will be used to study tourism destination marketing strategies. Specifically, big data processing frameworks such as Hadoop and Spark will be used for data processing, programming languages such as Python and R will be used for data analysis, machine learning algorithms will be used for data modeling, and data visualization tools will be used for results presentation.

(1)
Big data processing:

For large-scale tourism data, big data processing frameworks such as Hadoop and Spark are used for distributed processing. In the MapReduce model of Hadoop, data is divided into several small blocks and distributed to each node of the cluster for processing. Spark, on the other hand, provides more efficient memory computing capabilities and is suitable for analysis tasks that require repeated data access.
(2)
Data analysis:

The study will use programming languages such as Python and R for data analysis. Both languages have powerful data processing and statistical analysis functions, as well as rich libraries and tools, such as Python’s library Pandas, NumPy, Scikit-learn, and R’s library dplyr, ggplot2, caret, etc.
(3)
Data modeling:

The study will apply machine learning algorithms for data modeling to predict and interpret destination choice and satisfaction. For example, algorithms such as decision trees, random forests or support vector machines can be used to construct prediction models, and methods such as regression analysis or principal component analysis can be used for explanatory analysis.

Suppose a linear regression model is used to predict the satisfaction of tourist destinations, and the model can be expressed as Eq. (2).

$\displaystyle Y=\beta_{0}+\beta_{1}X_{1}+\beta_{2}X_{2}+\ldots+\beta_{p}X_{p}+\varepsilon$ (2)

Where, $Y$ represents the degree of satisfaction, $X_{1},X_{2},\ldots,X_{p}$ represents the factors that affect the degree of satisfaction (such as service quality, environmental quality, etc.), $\beta_{0},\beta_{1},\ldots,\beta_{p}$ is the parameter of the model, and $\varepsilon$ is the error term.
(4)
Data visualization:

Data visualization tools such as Tableau and PowerBI will be used to present the analysis results in the form of charts for easy understanding and interpretation. For example, the scatter chart can show the relationship between various factors and satisfaction, the bar chart can show the comparison of satisfaction of different tourist destinations, and the map can show the tourism popularity of different regions.

5. Data analysis and results

5.1 Result of factor analysis

Factor analysis is a statistical method used to explore the underlying structure behind a large number of correlated variables. In this study, factor analysis is used to study the characteristics of tourist destinations and tourist behavior. Specifically, factor analysis is carried out on the following variables: natural environment, cultural atmosphere, service quality, facilities, tourist consumption level, satisfaction, etc.

In this study, two major factors were identified through factor analysis, which explained most of the variable differences.

Factor 1, named “destination attraction”, is highly related to the natural environment, cultural atmosphere and facilities of the tourist destination.

Factor 2, named “tourist experience”, is highly related to service quality, tourist consumption level, satisfaction and other factors.

The factor load matrix is shown in Fig. 4.

Figure 4.

Factor load matrix of factor analysis results.

Each element of the factor load matrix represents the weight of the corresponding variable on each factor. The higher the weight is, the stronger the correlation between the variable and the factor is. Therefore, through factor analysis, the research can combine multiple related variables into a few factors, thus simplifying the complexity of the analysis and revealing the structure behind the data. In the subsequent analysis, the research will use these two factors as the main influencing factors of the tourism destination marketing strategy.

5.2 Results of big data analysis

In the big data analysis of this study, the above factor analysis results are used as input, with the goal of identifying the impact of tourism destination marketing strategies on factor 1 (destination attraction) and factor 2 (tourist experience).

Firstly, each component of the tourism destination marketing strategy is quantified and sorted according to the correlation with factor 1 and factor 2. For example, it is found that marketing strategies with strong correlation with factor 1 mainly promote natural and cultural resources in tourist destinations, while marketing strategies with strong correlation with factor 2 mainly improve service quality and satisfaction.

Then, a prediction model based on big data (e.g., random forest or support vector machines) was used to predict the effects of different marketing strategies on the two factors. The model is trained on a large amount of historical data, including detailed information about the destination, specific content of the marketing strategy, feedback from tourists, etc.

With the predictive results of these models, it is possible to identify which marketing strategies are most effective in enhancing the attractiveness of the destination and the visitor experience. For example, models may show that enhanced promotion of cultural activities and improved training of service personnel can significantly improve visitors’ overall evaluation of a particular destination. The results of these analyses provide specific, data-driven insights to travel destinations to help develop more accurate and effective marketing strategies.

Finally, the results were visualized to help better understand the effects of various marketing strategies. Here is the result of an example, Fig. 5.

Figure 5.

Data result analysis.

In the figure above, the higher the value, the greater the impact of the marketing strategy on the corresponding factor. Therefore, through big data analysis, more in-depth insights can be obtained to develop more effective tourism destination marketing strategies.

5.3 Correlation analysis

After big data analysis and factor analysis, the study further explored the relationship between different variables. In particular, we looked at the correlation between community engagement, online attention and destination appeal, which were identified as key factors in tourism destination marketing in the factor analysis above.

In tourism destination marketing strategies, community engagement refers to the level of activity of local community members in promoting the destination, while online attention relates to the level of discussion and attention on the destination in the online media. These two factors are closely related to destination attractiveness, as they directly affect the popularity of the tourist destination and the perception of tourists.

To explore the relationship between these factors, the study used the Pearson correlation coefficient, which is a measure of the linear relationship between two variables. The Pearson correlation coefficient is expressed in Eq. (3) as follows:

$\displaystyle r_{xy}=\frac{\sum\limits_{i=1}^{n}{\left({x_{i}-\bar{x}}\right)}% \left({y_{i}-\bar{y}}\right)}{\sqrt{\sum\limits_{i=1}^{n}{\left({x_{i}-\bar{x}% }\right)^{2}}}\sqrt{\sum\limits_{i=1}^{n}{\left({y_{i}-\bar{y}}\right)^{2}}}}$ (3)

Where $r_{xy}$ is the Pearson correlation coefficient of $x$ and $y$ , $x_{i}$ and $y_{i}$ are single observed values, and $\bar{x}$ and $\bar{y}$ are their respective average values.

After calculation, the correlation matrix is obtained (value close to 1 indicates strong correlation, value close to $-$ 1 indicates strong negative correlation, and value close to 0 indicates no correlation). Specific correlation matrix is shown in Fig. 6.

As can be seen from the figure above, there is a strong positive correlation between these three factors. Among them, the correlation between destination attraction and community participation is the strongest, reaching 0.72. This means that when a destination has high appeal, community participation is usually high. The correlation between online media attention and community engagement was the lowest at 0.57. The results show that online media attention, destination attraction and community participation are significantly positively correlated. In addition, through correlation analysis, we can better understand how these factors jointly affect the marketing effect of tourist destinations, so as to provide more references for the optimization of actual marketing strategies.

5.4 Result analysis

In this study, a detailed factor analysis of big data is carried out, and based on these analysis results, an in-depth study is conducted on the tourism destination marketing strategy. The research shows that different marketing strategies have different effects on the attraction of tourist destinations and the improvement of tourist experience. Therefore, tourist destinations need to choose appropriate strategies according to their own characteristics and the needs of target tourists.

From the result of factor analysis, the research can divide tourists’ choice factors for tourist destinations into two categories: destination attraction (including natural resources and cultural resources) and tourist experience (including service quality and satisfaction). These two factors together determine tourists’ choice behavior and satisfaction.

From the results of big data analysis, it is found that marketing strategies to enhance natural resources and cultural resources have a significant effect on the attractiveness of destinations; The marketing strategy of improving service quality and satisfaction has a significant effect on improving tourists’ experience. This shows that tourism destinations need to comprehensively consider the two aspects of enhancing destination attraction and improving tourist experience when formulating marketing strategies, so as to achieve the best marketing effect.

Based on these analysis results, tourism destinations can adopt the following specific marketing strategies:

For natural and cultural resources, increased investment can be made to improve their accessibility and presentation, while increasing the visibility and attractiveness of these resources through digital media and social networks.

To improve service quality and satisfaction, tourism destinations should pay attention to staff training, optimize visitor service processes, and continuously improve services through user feedback.

The specific results of factor analysis and big data analysis are as follows, as shown in Table 3.

Table 3
Analysis of results

Analysis result	Factor 1 (destination attraction)	Factor 2 (Visitor experience)
Factor analysis result	The promotion of natural resources and cultural resources has achieved remarkable results	The effect of improving service quality and satisfaction is remarkable
Big data analysis results	Promoting natural and cultural resources can significantly increase attractiveness	Improving service quality and satisfaction can significantly improve the experience

Figure 6.

Influences on marketing strategies of tourist destinations.

To sum up, the results of big data analysis and factor analysis provide a reference for tourism destinations to develop effective marketing strategies, thus helping them enhance tourism attraction, improve tourist experience, and ultimately achieve higher tourism performance.

5.5 Problems and challenges in the research

Although this study has achieved some meaningful results, there are still some problems and challenges in the research process:

Data quality and integrity issues: Big data collection and processing needs to face data quality and integrity issues. For example, there may be noise, errors, or missing data, which may affect the results of the analysis. Therefore, it is necessary to pay attention to data cleaning and sorting at the stage of data collection and processing.

Adaptability of models: Factor analysis is a statistical model whose adaptability depends on the characteristics of the data. In this study, it was assumed that the data satisfied the assumptions of factor analysis, but this may not always be true in real situations.

Challenges of factor interpretation: In factor analysis, the interpretation of factors needs to be based on subjective judgment, which may bring some uncertainty. Therefore, multi-angle and multi-dimensional understanding and interpretation factors are needed.

Challenges of Big data technology: Although big data technology provides rich data and powerful analytical capabilities, it also has some challenges, such as data storage and processing requirements, data security and privacy issues, as well as the difficulty of learning and application of big data technology.

Table 4 summarizes the main issues and challenges in this study.

Table 4
Problems and challenges in the research

Problems and challenges	Description
Data quality and integrity issues	It is necessary to pay attention to data cleaning and organizing at the data collection and processing stage
The adaptability of the model	You need to verify that the data meets the assumptions of factor analysis
The challenge of factor interpretation	Need to understand and explain factors based on subjective judgment
Challenges of big data technology	Issues such as data storage and processing, data security and privacy, as well as the difficulty of learning and applying big data technologies need to be addressed

To sum up, a deeper understanding and solution of these issues and challenges is needed to make more effective use of big data and factor analysis techniques to enhance the effectiveness of tourism destinations’ marketing strategies.

5.6 Theoretical and practical enlightenment of tourism destination marketing strategies based on big data

Through the research of big data-driven tourism destination marketing strategy, we get some theoretical and practical enlightenment:

(1)
Theoretical enlightenment:

The formulation of marketing strategies needs data support: This study shows that big data and factor analysis can provide strong data support for the formulation of tourism destination marketing strategies. This can not only help to understand the needs and behaviors of tourists, but also help to find and solve the problem of marketing strategy.

Application of factor analysis: Factor analysis, as a statistical model, has a wide range of applications in big data analysis. The results of this study show that through factor analysis, important factors can be extracted from a large number of data, which has important theoretical value for understanding and improving tourism destination marketing strategies.
(2)
Practical enlightenment:

Application of big data technology: Big data technology can help collect and process a large amount of data to support the formulation and optimization of tourism destination marketing strategies. Therefore, tourism destinations need to strengthen the application of big data technology and improve the ability of data analysis.

Marketing strategy optimization: Through data analysis, we can find out the problems and improvement direction of marketing strategy. For example, through factor analysis, we can find out the main factors that affect the choice of tourists, and then optimize the marketing strategy according to these factors.

The theoretical and practical implications of this study are summarized in Table 5.

Table 5
Theoretical and practical enlightenment of tourism destination marketing strategies based on big data

Type of revelation Enlightenment

Theoretical enlightenment The development of marketing strategy needs data support; Factor analysis is widely used in big data analysis

Practical enlightenment Tourism destinations need to strengthen the application of big data technology; Through data analysis, we can find out the problems and improvement directions of marketing strategy

In general, this study provides a research method of tourism destination marketing strategy based on big data, which is of great significance to promote the theoretical research and practical application of tourism destination marketing strategy.
6. Conclusions and suggestions

Type of revelation	Enlightenment
Theoretical enlightenment	The development of marketing strategy needs data support; Factor analysis is widely used in big data analysis
Practical enlightenment	Tourism destinations need to strengthen the application of big data technology; Through data analysis, we can find out the problems and improvement directions of marketing strategy

This study makes a comprehensive exploration of the big data driven tourism destination marketing strategy. Firstly, the application status of big data in the tourism industry is reviewed, and the existing strategies of tourism destination marketing are discussed in detail. Then, using the theory of big data analysis and factor analysis, a series of research methods are designed and implemented.

Through the processing and factor analysis of a large number of collected data, a wealth of analysis results are obtained. These results reveal the influence of big data in tourism destination marketing strategies and provide the possibility of optimizing marketing strategies. In addition, the problems and challenges encountered in the process of data processing and analysis were also found, which has important guiding significance for further improvement of research methods in the future.

The limitations of this study are mainly reflected in the diversity of data sources and the limitation of data volume. Limited by access and scope of data, it may not be possible to fully cover all destinations and all types of visitor data. Therefore, there may be some bias in the research results, and the potential impact on future tourism marketing strategies should be carefully evaluated. Future research should focus on collecting a wider range of data to improve the accuracy and reliability of the study.

The main contribution of this study is to apply big data technology to the analysis and optimization of tourism destination marketing strategy, which provides a new perspective and method. The study recognizes that big data technology can provide strong support for the formulation and optimization of tourism destination marketing strategies, while factor analysis can help extract the main factors influencing tourists’ choices from a large amount of data. On the basis of this study, future studies can further explore the application of big data in other tourism-related fields, such as tourism product development and tourist behavior prediction, with a view to providing a more comprehensive and in-depth research perspective and method.

In general, this study is of great significance to promote the theoretical research and practical application of tourism destination marketing strategy. Future studies can further explore the application of big data in other tourism-related fields on the basis of this study, with a view to providing more comprehensive and in-depth research perspectives and methods.

Footnotes

Funding

This research was funded by The Project of Improving the Basic Ability of Scientific Research of Young and Middle-aged Teachers in Guangxi Universities: Research on the mechanism and path of integration of Industry, education and City in Guangxi University Cluster Area (Project Number: 2022KY1637).

References

Duro

Osorio

Perez-Laborda

Fernández-Fernández

. Measuring tourism markets vulnerability across destinations using composite indexes. J Destin Mark Manage. 2022; 25: 100731.

Oender

Gunter

Gindl

. Utilizing Facebook statistics in tourism demand modeling and destination marketing. J Travel Res. 2020; 59(2): 195-208.

Rather

. Customer experience and engagement in tourism destinations: the experiential marketing perspective. J Travel Tour Mark. 2020; 37(1): 15-32.

Gardiner

Scott

. Destination innovation matrix: A framework for new tourism experience and market development. J Destin Mark Manage. 2018; 10: 122-131.

Bastiaansen

Straatman

Mitas

Stekelenburg

Jansen

. Emotion measurement in tourism destination marketing: A comparative electroencephalographic and behavioral study. J Travel Res. 2022; 61(2): 252-264.

Vodopivec

Ruzzier

. Opportunities in identifying and marketing windsport tourism destinations: High-resolution wind analysis. Sustainability-Basel. 2022; 14(24): 16589.

Fjelldal

Kralj

Moyle

. Profanity in viral tourism marketing: A conceptual model of destination image reinforcement. J Vacat Mark. 2022; 28(1): 52-63.

Kilipiri

Papaioannou

Kotzaivazoglou

. Social media and influencer marketing for promoting sustainable tourism destinations: The Instagram case. Sustainability-Basel. 2023; 15(8): 6374.

Chang

Chiang

. Is virtual reality technology an effective tool for tourism destination marketing? A flow perspective. J Hosp Tour Technol. 2022; 13(3): 427-440.

10.

Ruiz-Meza

Sotaquirá

Montoya-Torres

. Effects of tourism planning and marketing strategies on destination brand equity: A system dynamics model. J Simul. 2022.

11.

Yin

. The marketing of destination distinctiveness: The power of tourism short videos with enjoyability and authenticity. Curr Issues Tour. 2023.

12.

Perkins

Khoo-Lattimore

Arcodia

. Collaboration in marketing regional tourism destinations: Constructing a business cluster formation framework through participatory action research. J Hosp Tour Manag. 2021; 46: 347-359.

13.

Ketter

Avraham

. #StayHome today so we can #TravelTomorrow: tourism destinations’ digital marketing strategies during the COVID-19 pandemic. J Travel Tour Mark. 2021; 38(8): 819-832.

14.

Mainolfi

Marino

. Destination beliefs, event satisfaction and post-visit product receptivity in event marketing. Results from a tourism experience. J Bus Res. 2020; 116: 699-710.

15.

Liu

Jiang

Gan

. The antecedent and consequence behaviour of sustainable tourism: integrating the concepts of marketing strategy and destination image. Asia Pac J Tour Res. 2021; 26(8): 829-848.

16.

Gaffar

Tjahjono

Abdullah

Sukmayadi

. Like, tag and share: bolstering social media marketing to improve intention to visit a nature-based tourism destination. Tour Rev. 2021.

17.

Xiao

Fang

Lin

Chen

. A framework for quantitative analysis and differentiated marketing of tourism destination image based on visual content of photos. Tourism Manage. 2022; 93: 104585.

18.

Yang

Lei

Zhang

Song

Wang

. Altruistic motivation, moral elevation and tourism support behavior: An empirical study based on cause-related marketing in tourist destinations. Sustainability-Basel. 2023; 15(5): 3888.

User ID	Tourist destination	Score	Comment content
1	A	4	“Beautiful scenery and good service.”
2	B	5	“I really like the culture here.”
3	A	3	“Transportation is not very convenient.”
$\ldots$	$\ldots$	$\ldots$	$\ldots$