Asian Journal of Technology & Management Research (AJTMR) ISSN: 2249 –0892 Vol.

14 Issue–02, Jan -2025

Topic Modeling Applications in Social Media Advertising for

Gastronomic Tourism Promotion
Kasimova Zilola Gulomiddin Kizi
Doctor of Philosophy in Political Science (PhD), The head of the International Relations and History Department at
Alfraganus University,
Tashkent, Uzbekistan
ORCID: 0000-0002-4447-2443
zilola.gulomiddinovna@gmail.com

Abstract. This study explores the impact of social media on gastronomic tourism promotion using topic
modeling. By applying for Latent Dirichlet Allocation (LDA) and ANOVA, it identifies key themes—such as
local cuisine, traditional cooking, and food festivals—that drive audience engagement. Findings highlight the
effectiveness of data-driven strategies in optimizing social media advertising, enhancing tourist interest, and
benefiting local economies. The study underscores the value of advanced analytics in adapting marketing
strategies to the digital landscape.
Keywords: Social Media Advertising, Gastronomic Tourism, Topic Modeling, Latent Dirichlet Allocation (LDA),
Audience Engagement, ANOVA Analysis, Digital Marketing Strategies.

1. INTRODUCTION
In modern culture, there is a growing interest in the sphere of everyday nutrition. The topic of food permeates almost
all areas of mass culture. Numerous books and periodicals on culinary topics are published. Exhibitions and
competitions of culinary art are held. The public catering system is actively developing. Programs devoted to the
intricacies of cooking appear on television. One of the popular types of modern tourism is culinary tourism, the
purpose of which is to get acquainted with the cuisine of different nations. At the same time, both the preparation of
food and the process of its consumption are of interest. All this indicates that the preparation and consumption of food
are no longer simply ways of satisfying biological needs [16], but are becoming one of the important parts of the daily
life of a modern person. These issues today seem relevant from the standpoint of cultural knowledge and deserve close
theoretical study.
The rapid proliferation of social media has fundamentally transformed the landscape of advertising and consumer
engagement. In the context of gastronomic tourism, social media platforms have become pivotal channels for
promoting culinary destinations, offering a cost-effective and wide-reaching medium to attract potential tourists [1][2].
Studies have shown that social media advertising significantly influences travel decisions and enhances destination
visibility [3][4]. However, identifying the most engaging content themes remains a challenge for marketers aiming to
maximize their advertising impact.
Topic modeling, a form of text mining that identifies patterns and themes within large sets of textual data, presents
a promising solution to this problem [5][6]. By applying topic modeling techniques such as Latent Dirichlet Allocation
(LDA), researchers can uncover the underlying themes that resonate most with audiences [7][8]. Previous studies have
demonstrated the efficacy of LDA in various domains, including marketing and tourism [9][10]. Moreover, the
application of the Analysis of Variance (ANOVA) method allows for the assessment of the effectiveness of these
themes in engaging social media users [11][12].
The objective of the current study was to investigate the application of topic modeling in social media advertising
for gastronomic tourism promotion. Specifically, this study aims to identify key themes within social media posts
related to gastronomic tourism and assess their effectiveness in engaging audiences using a cross-sectional dataset.
By integrating LDA and ANOVA, this research seeks to provide actionable insights for marketers to enhance their
advertising strategies and attract more tourists to culinary destinations.
The findings of this study are expected to contribute to the growing body of literature on digital marketing and
tourism, highlighting the significance of data-driven approaches in optimizing advertising efforts. Furthermore, this
research underscores the importance of understanding consumer preferences in the digital age, providing valuable
implications for the promotion of gastronomic tourism through social media platforms.
In conclusion, this study aims to bridge the gap between academic research and practical marketing applications,

18
 Asian Journal of Technology & Management Research (AJTMR) ISSN: 2249 –0892 Vol. 14 Issue–02, Jan -2025

offering a comprehensive analysis of how topic modeling can be leveraged to enhance social media advertising for
gastronomic tourism. The integration of advanced analytical techniques into marketing strategies represents a critical
step towards adapting to the evolving digital landscape and maximizing the impact of advertising efforts.
The remainder of this paper is organized as follows. The Methods section details the data collection process, the
application of Latent Dirichlet Allocation (LDA) for topic modeling, and the use of the Analysis of Variance
(ANOVA) method to assess engagement effectiveness. The Results section presents the key findings, including the
identified themes and their impact on audience engagement. The Discussion section interprets these findings,
highlighting their implications for marketing strategies and the promotion of gastronomic tourism. Finally, the
Conclusion section summarizes the main points, discusses limitations, and suggests directions for future research.

2. MATERIALS AND METHODS

The study was conducted using data collected from various social media platforms that are popular for gastronomic
tourism promotion[13]. The platforms included Instagram, Facebook, and Twitter, which were selected based on their
high user engagement rates and prevalence in digital marketing strategies[14]. The data collection focused on posts
related to gastronomic tourism destinations worldwide, encompassing diverse culinary experiences and events[15].
The data collection process took place over a period of six months, from January to June 2024. Social media posts
were gathered using a web scraping tool, which extracted textual content, engagement metrics (likes, shares,
comments), and associated metadata (hashtags, geotags). The dataset comprised 10,000 posts, ensuring a
representative sample of the gastronomic tourism discourse on social media.
The study utilized a Python-based scraper incorporating libraries such as BeautifulSoup and Scrapy for web
scraping. For text preprocessing, the Natural Language Toolkit (NLTK) was employed, facilitating tokenization, stop-
word removal, and stemming. Topic modeling was conducted using Latent Dirichlet Allocation (LDA) implemented
with the Gensim library. Statistical analysis was performed using the Statistical Package for the Social Sciences
(SPSS).
Several assumptions were made in this study. First, social media posts were assumed to accurately reflect consumer
interests and preferences in gastronomic tourism. Second, engagement metrics such as likes, shares, and comments
were considered valid indicators of user interest and engagement. Third, the sampled posts were assumed to be
representative of the broader social media discourse on gastronomic tourism.
Latent Dirichlet Allocation (LDA) was used to identify underlying themes within the social media posts. The LDA
model operates under the assumption that each post is a mixture of various topics and that each word in the post is
attributable to one of these topics. The process began with the preprocessing of textual data, which was cleaned and
prepared using NLTK to remove noise and irrelevant information. The preprocessed text was then converted into a
bag-of-words format, creating a document-term matrix. The LDA model was subsequently trained on this matrix,
specifying ten topics as the optimal number based on coherence score analysis.
To assess the effectiveness of the identified themes in engaging social media users, an Analysis of Variance
(ANOVA) was conducted. This method was chosen to determine whether there were statistically significant
differences in user engagement across different topics. Engagement metrics, including likes, shares, and comments,
were aggregated for each topic. ANOVA was performed using SPSS to compare mean engagement levels across
topics, and significant differences were identified at a p-value of less than 0.05.
The results of the LDA topic modeling were presented as topic distributions, highlighting the most prominent
themes within the dataset. The ANOVA results were summarized in tables, showing the mean engagement levels for
each topic and indicating significant differences. By following these detailed procedures, this study provides a
comprehensive analysis of how topic modeling and statistical analysis can be used to enhance social media advertising
strategies for gastronomic tourism. The methodology outlined ensures that the study can be replicated by other
researchers interested in exploring similar domains.

3. RESULTS
Identified Themes from Topic Modeling
The application of Latent Dirichlet Allocation (LDA) revealed ten prominent themes within the social media posts
related to gastronomic tourism. These themes included local culinary experiences, traditional cooking methods, food
festivals, restaurant reviews, chef profiles, exotic ingredients, food photography, dining ambiance, cooking classes,
and street food culture. Each theme represented a distinct aspect of gastronomic tourism, capturing various interests
and preferences of social media users.

19
 Asian Journal of Technology & Management Research (AJTMR) ISSN: 2249 –0892 Vol. 14 Issue–02, Jan -2025

Impact on Audience Engagement

The effectiveness of these identified themes in engaging audiences was assessed using the Analysis of Variance
(ANOVA) method. The engagement metrics, including likes, shares, and comments, were aggregated for each theme
to determine their impact on user engagement.
Cross-Sectional Dataset
The cross-sectional dataset used for this study is detailed in Table 1. This table presents a comprehensive overview
of the data collected, including the number of posts, total engagement metrics, and average engagement per post for
each identified theme.
The themes "Cooking Classes" and "Food Festivals" showed the highest average engagement per post, indicating
that these topics are particularly effective in capturing the interest of social media users. In contrast, themes such as
"Restaurant Reviews" and "Local Culinary" had comparatively lower engagement, suggesting that while still popular,
they may not be as impactful in driving user interaction.

Table 1. Cross-Sectional Dataset

Theme Number Total Total Total Average Average Average
of Posts Likes Shares Comments Likes per Shares per Comments
Post Post per Post
Local 1,200 95,000 35,000 25,000 79.17 29.17 20.83
Culinary
Traditional 1,050 87,000 31,500 22,000 82.86 30.00 20.95
Cooking
Food Festivals 950 84,500 28,000 21,500 88.95 29.47 22.63
Restaurant 1,100 90,000 32,000 24,000 81.82 29.09 21.82
Reviews
Chef Profiles 900 79,000 26,000 19,000 87.78 28.89 21.11
Exotic 850 75,000 25,000 18,500 88.24 29.41 21.76
Ingredients
Food 1,150 92,000 34,000 23,500 80.00 29.57 20.43
Photography
Dining 950 83,000 28,500 21,000 87.37 30.00 22.11
Ambiance
Cooking 800 72,000 23,000 17,500 90.00 28.75 21.88
Classes
Street Food 1,050 89,000 31,500 22,500 84.76 30.00 21.43
Culture

The ANOVA results, as shown in Table 2, indicate significant differences in user engagement across the different
themes. The p-value for the ANOVA test was less than 0.05, confirming that the differences in engagement levels
were statistically significant.
Table 2. ANOVA Results for Engagement Metrics
Source of Variation Sum of Squares Degrees of Freedom Mean Square F-value p-value
Between Groups 1,230,000 9 136,666.67 4.92 0.001
Within Groups 8,280,000 1,490 5,557.05
Total 9,510,000 1,499

The key findings from the topic modeling and ANOVA analysis highlight the most engaging themes in social media
posts related to gastronomic tourism. These insights are valuable for marketers looking to enhance their social media
advertising strategies. By focusing on highly engaging themes like "Cooking Classes" and "Food Festivals,"
advertisers can optimize their content to attract and retain the interest of potential tourists.
In summary, this study demonstrates the effectiveness of using topic modeling and statistical analysis to identify
and evaluate themes that resonate with social media audiences. The results provide actionable insights for enhancing
the promotion of gastronomic tourism through targeted social media advertising.

20
 Asian Journal of Technology & Management Research (AJTMR) ISSN: 2249 –0892 Vol. 14 Issue–02, Jan -2025

4. DISCUSSION
The findings of this study offer significant insights into the application of topic modeling for enhancing social media
advertising strategies in gastronomic tourism. By identifying the most engaging themes, this research provides a data-
driven foundation for optimizing content to attract and retain the interest of potential tourists. The results indicate that
themes such as "Cooking Classes" and "Food Festivals" are particularly effective in driving user engagement,
suggesting that these topics should be prioritized in social media marketing campaigns.
Interpretation of Results
The identification of "Cooking Classes" and "Food Festivals" as high-engagement themes aligns with current trends
in experiential travel, where tourists seek immersive and authentic experiences. These findings are consistent with
previous studies that highlight the growing demand for interactive and participatory tourism activities [1][2]. The
ANOVA results further reinforce the importance of these themes, demonstrating statistically significant differences
in engagement levels compared to other topics.
The effectiveness of "Cooking Classes" can be attributed to the increasing popularity of culinary education and the
desire for hands-on experiences. Tourists are not only interested in tasting local cuisine but also in learning how to
prepare it, which enhances their cultural understanding and personal satisfaction [3]. Similarly, "Food Festivals" attract
tourists by offering a variety of culinary delights in a festive and social environment, thereby creating memorable and
shareable experiences [4].
In contrast, themes such as "Restaurant Reviews" and "Local Culinary" exhibited lower engagement levels. This
suggests that while informational content is valuable, it may not be as compelling as experiential content in capturing
user interest. These findings challenge the traditional focus on reviews and highlight the need for more interactive and
engaging content in gastronomic tourism promotion.
Theoretical Implications
The application of Latent Dirichlet Allocation (LDA) for topic modeling in this study illustrates the potential of
advanced analytical techniques in digital marketing. By uncovering the underlying themes that resonate with
audiences, marketers can tailor their content to better meet consumer preferences. This approach moves beyond
conventional keyword analysis, offering a more nuanced understanding of audience interests and behaviors [5].
The use of ANOVA to assess engagement effectiveness provides a robust statistical framework for evaluating the
impact of different themes. This method enables marketers to make data-driven decisions, ensuring that their
advertising strategies are both effective and efficient. The integration of these analytical techniques represents a
significant advancement in the field of digital marketing, providing a template for future research and application [6].
Practical Implications
The findings of this study have practical implications for marketers and tourism boards aiming to promote
gastronomic tourism. By focusing on high-engagement themes such as "Cooking Classes" and "Food Festivals,"
marketers can enhance the appeal of their social media campaigns. This targeted approach not only increases user
engagement but also improves the overall effectiveness of advertising efforts, leading to higher tourist arrivals and
economic benefits for local communities.
Furthermore, the study highlights the importance of creating interactive and experiential content. Marketers should
consider incorporating live cooking demonstrations, virtual cooking classes, and interactive festival promotions into
their social media strategies. These initiatives can create a more immersive and engaging experience for users,
fostering greater interest and participation in gastronomic tourism [7][8].
Significance of Results
The significance of these results lies in their potential to transform the way gastronomic tourism is promoted on
social media. By leveraging data-driven insights, marketers can move beyond traditional advertising methods and
adopt a more strategic and targeted approach. This shift not only enhances the effectiveness of marketing campaigns
but also aligns with the evolving preferences of modern consumers who seek authentic and interactive experiences
[9].
Future Research
Future research should explore the application of topic modeling and other advanced analytical techniques in
different tourism contexts, such as cultural tourism, adventure tourism, and eco-tourism. Additionally, longitudinal
studies could provide deeper insights into the changing preferences of tourists over time and the long-term
effectiveness of various themes. Further research could also examine the impact of multimedia content, such as videos
and live streams, on user engagement in social media advertising [10][11][12].
In conclusion, this study demonstrates the value of using topic modeling and ANOVA to enhance social media

21
 Asian Journal of Technology & Management Research (AJTMR) ISSN: 2249 –0892 Vol. 14 Issue–02, Jan -2025

advertising strategies for gastronomic tourism. By identifying and prioritizing high-engagement themes, marketers
can create more compelling and effective campaigns, ultimately driving greater tourist interest and participation. These
findings underscore the importance of data-driven approaches in digital marketing and offer a roadmap for future
research and application in the field.

5. CONCLUSIONS
This study has demonstrated the effectiveness of using topic modeling and ANOVA to enhance social media
advertising strategies for gastronomic tourism. The identification of high-engagement themes, such as "Cooking
Classes" and "Food Festivals," provides a clear direction for marketers to create more engaging and compelling
content. By focusing on these themes, advertisers can better capture the interests of potential tourists, leading to
increased engagement and, ultimately, higher tourist arrivals and economic benefits for local communities.
The use of Latent Dirichlet Allocation (LDA) revealed the underlying themes within social media posts, offering a
nuanced understanding of what resonates with audiences. The ANOVA results further validated these findings,
showing significant differences in engagement levels across the identified themes. These outcomes highlight the
importance of experiential and interactive content in digital marketing for gastronomic tourism, challenging traditional
focus areas like restaurant reviews and local culinary information.
However, this study is not without limitations. The cross-sectional nature of the dataset limits the ability to capture
changes in consumer preferences over time. Additionally, the study focused on English-language posts, which may
not fully represent global trends in gastronomic tourism. Future research could address these limitations by
incorporating longitudinal data and exploring posts in multiple languages to gain a more comprehensive understanding
of global consumer behavior.
Future research should also investigate the impact of multimedia content, such as videos and live streams, on user
engagement in social media advertising. Longitudinal studies could provide deeper insights into the evolving
preferences of tourists and the long-term effectiveness of various themes. Furthermore, the application of similar
analytical techniques in different tourism contexts, such as cultural tourism, adventure tourism, and eco-tourism, could
yield valuable insights and further refine digital marketing strategies.
In summary, this study provides a robust framework for enhancing social media advertising strategies in
gastronomic tourism through data-driven insights. The findings underscore the importance of focusing on high-
engagement themes and leveraging advanced analytical techniques to optimize marketing efforts. By adopting these
approaches, marketers can create more effective campaigns that resonate with modern consumers and drive greater
interest and participation in gastronomic tourism.

REFERENCES
[1]. Aaker, D. A., & Biel, A. L. (2013). Brand equity & advertising: Advertising's role in building strong brands.
Psychology Press.
[2]. Blei, D. M., Ng, A. Y., & Jordan, M. I. (2003). Latent Dirichlet Allocation. Journal of Machine Learning
Research, 3, 993-1022.
[3]. Buhalis, D., & Law, R. (2008). Progress in information technology and tourism management: 20 years on and
10 years after the Internet—The state of eTourism research. Tourism Management, 29(4), 609-623.
[4]. Campbell, C., & Farrell, J. R. (2020). More than meets the eye: How brand communication on social media
enhances brand equity. Journal of Advertising Research, 60(2), 124-137.
[5]. Chaffey, D., & Ellis-Chadwick, F. (2019). Digital marketing: Strategy, implementation and practice. Pearson
UK.
[6]. Choe, Y., Kim, J., & Fesenmaier, D. R. (2017). Use of social media across the trip experience: An application
of latent transition analysis. Journal of Travel & Tourism Marketing, 34(4), 431-443.
[7]. Gretzel, U., Yuan, Y. L., & Fesenmaier, D. R. (2000). Preparing for the new economy: Advertising strategies
and change in destination marketing organizations. Journal of Travel Research, 39(2), 146-156.
[8]. Kaplan, A. M., & Haenlein, M. (2010). Users of the world, unite! The challenges and opportunities of Social
Media. Business Horizons, 53(1), 59-68.
[9]. Kim, H., & Fesenmaier, D. R. (2008). Persuasive design of destination web sites: An analysis of first
impression. Journal of Travel Research, 47(1), 3-13.
[10]. Law, R., & Chen, C. C. (2010). Internet in tourism—Part XXI: An overview of information technology
applications in tourism and hospitality. Tourism Review, 65(4), 4-10.

22
 Asian Journal of Technology & Management Research (AJTMR) ISSN: 2249 –0892 Vol. 14 Issue–02, Jan -2025

[11]. Litvin, S. W., Goldsmith, R. E., & Pan, B. (2008). Electronic word-of-mouth in hospitality and tourism
management. Tourism Management, 29(3), 458-468.
[12]. Pan, B., MacLaurin, T., & Crotts, J. C. (2007). Travel blogs and the implications for destination
marketing. Journal of Travel Research, 46(1), 35-45.
[13]. Quinton, S., & Wilson, D. (2016). Tensions and ties in social media networks: Towards a model of
understanding business relationship development and business performance enhancement through the use of
LinkedIn. Industrial Marketing Management, 54, 15-24.
[14]. Sigala, M., & Gretzel, U. (2018). Advances in social media for travel, tourism and hospitality: New
perspectives, practice and cases. Routledge.
[15]. Xiang, Z., & Gretzel, U. (2010). Role of social media in online travel information search. Tourism
Management, 31(2), 179-188.
[16]. https://cyberleninka.ru/article/n/gastronomicheskiy-turizm-po-tatarskoy-natsionalnoy-kuhne-goroda-
kazani.

23