STAP Journal of Security Risk Management

ISSN: 3080-9444 (Online)

A Smart Dashboard Framework for Urban Tourism Risk Analysis Using Deep Learning and Machine Learning

by 

Adona Kulathinal Josephi ;

Mahmud Maqsood

PDF logoPDF

Published: 2026

Abstract

The study proposes an intelligent framework to evaluate tourism safety in Indian cities by integrating diverse, real-world data source, including crime statistics, hotel ratings, and user reviews. The methodology employs advanced artificial intelligence techniques, notably a fine-tuned BERT model for classifying user reviews into safety-related sentiment categories and XGBoost for predicting crime pattern prediction and city-level safety score computation. The analytical pipeline includes comprehensive data preprocessing, sentiment classification, predictive modeling, and cluster analysis to uncover patterns and associations. Cities are segmented into distinct risk categories based on crime density and public sentiment, enabling nuanced safety profiling. A noteworthy finding is the strong inverse relationship between tourist satisfaction and crime rates, underscoring the significant influence of safety perceptions on a destination’s attractiveness. The final output is an interactive Power BI dashboard that supports real-time filtering, geospatial analysis, sentiment mapping, and predictive insights. This decision-support system enables travelers to make informed choices, assists policymakers in identifying high-risk areas, and assists urban planners in designing targeted safety interventions. Overall, the research addresses a critical gap in tourism safety information and demonstrates the potential of AI in developing data-driven, transparent, and responsive tools for smart tourism management.

Keywords

Crime analyticstourism safetysentiment analysisBERTXGBoostpredictive modellingclusteringUrban intelligencePower BI dashboardsmart tourism

A Smart Dashboard Framework for Urban Tourism Risk Analysis Using Deep Learning and Machine Learning is licensed under CC BY 4.0CCBY

References

  1. George, R. (2003). Tourists’ perceptions of safety and security while visiting Cape Town. Tourism Management, 24(5), 575–585. https://doi.org/10.1016/S0261-5177(03)00003-7
  2. Yu, N., & Chen, J. (2022). Design of machine learning algorithm for tourism demand prediction. Computational and Mathematical Methods in Medicine, 2022, 1–9. https://doi.org/10.1155/2022/6352381
  3. Shchokin, R., Maziychuk, V., Mykhailyk, O., Kolomiiets, A., Akifzade, S., & Tymoshenko, Y. (2023). The impact of the crime rate on the hospitality and tourism industry in EU countries. GeoJournal of Tourism and Geosites, 46(1), 135–147. https://doi.org/10.30892/gtg.46115-1009
  4. Lisowska, A. (2017). Crime in tourism destinations: Research review. Turyzm, 27(1), 31–39. https://doi.org/10.1515/tour-2017-0004
  5. Cohen, E. (2018). Tourism-related crime: Towards a sociology of crime and tourism. Visions in Leisure and Business, 16(1). https://scholarworks.bgsu.edu/visions/vol16/iss1/2/
  6. Mawby, R. I., & Vakhitova, Z. I. (2022). Researching the relationship between tourism, crime and security: The tourism industry and the disenfranchised citizens. In The handbook of security (pp. 581–601). Springer. https://doi.org/10.1007/978-3-030-91735-7_27
  7. Chhabra, J., & Bhattacharjee, M. (2019). Analyzing tourist preferences in India to crime and threat of terrorism. International Journal of Research in Social Sciences, 9, 2249–2496.
  8. Hua, N., Li, B., & Zhang, T. (2020). Crime research in hospitality and tourism. International Journal of Contemporary Hospitality Management, 32(3), 1299–1323. https://doi.org/10.1108/IJCHM-09-2019-0750
  9. Brunt, P., Mawby, R., & Hambly, Z. (2000). Tourist victimisation and the fear of crime on holiday. Tourism Management, 21(4), 417–424. https://doi.org/10.1016/S0261-5177(99)00084-9
  10. Biagi, B., & Detotto, C. (2012). Crime as tourism externality. Regional Studies, 48(4), 693–709. https://doi.org/10.1080/00343404.2011.649005
  11. Johnny, L., & Jordan, L. (2007). Tourism and crime in the Caribbean: A case study of St Lucia. Annals of Leisure Research, 10(3–4), 475–497. https://doi.org/10.1080/11745398.2007.9686777
  12. Dash, D. P., Dash, A. K., & Parida, Y. (2024). Lethal attraction: Crime as tourism externality—Evidence from the Indian states. Asia Pacific Journal of Tourism Research, 1–17. https://doi.org/10.1080/10941665.2024.2426196
  13. Tiwari, V., & Omar, A. (2023). The impact of the hotel star rating system on tourists’ health safety and risk perceptions: A study based on tourists’ vacation experiences. Journal of Vacation Marketing. https://doi.org/10.1177/13567667231188880
  14. Álvaro, A., Koehler, M., Konstantinou, N., Pankin, P., Paton, N. W., & Sakellariou, R. (2023). Data preparation: A technological perspective and review. SN Computer Science, 4(4). https://doi.org/10.1007/s42979-023-01828-8
  15. Wu, Y., Jin, Z., Shi, C., Liang, P., & Zhan, T. (2024). Research on the application of deep learning-based BERT model in sentiment analysis. arXiv. https://arxiv.org/abs/2403.08217
  16. Kumar, R. V. (2021). Exploratory data analysis using R & RStudio. https://doi.org/10.13140/RG.2.2.24944.99843
  17. Nelson, L. S. (1998). The Anderson–Darling test for normality. Journal of Quality Technology, 30(3), 298–299. https://doi.org/10.1080/00224065.1998.11979858
  18. Jerez, J. M., Molina, I., García-Laencina, P. J., Alba, E., Ribelles, N., Martín, M., & Franco, L. (2010). Missing data imputation using statistical and machine learning methods in a real breast cancer problem. Artificial Intelligence in Medicine, 50(2), 105–115. https://doi.org/10.1016/j.artmed.2010.05.002
  19. Selvakumar, B., & Lakshmanan, B. (2022). Sentiment analysis on users’ reviews using BERT. Materials Today: Proceedings. https://doi.org/10.1016/j.matpr.2022.03.678
  20. Safat, W., Asghar, S., & Gillani, S. A. (2021). Empirical analysis for crime prediction and forecasting using machine learning and deep learning techniques. IEEE Access, 9, 1–15. https://doi.org/10.1109/ACCESS.2021.3078117
  21. Cui, M. (2020). Introduction to the k-means clustering algorithm based on the elbow method. https://doi.org/10.23977/ACCAF.2020.010102
  22. Gera, P., & Vohra, R. (n.d.). City crime profiling using cluster analysis.
  23. Catelli, R., Pelosi, S., & Esposito, M. (2022). Lexicon-based vs. BERT-based sentiment analysis: A comparative study in Italian. Electronics, 11(3), 374. https://doi.org/10.3390/electronics11030374
  24. Peters, M., Neumann, M., Zettlemoyer, L., & Yih, W.-T. (2018). Dissecting contextual word embeddings: Architecture and representation. arXiv. https://arxiv.org/abs/1808.08949
  25. Athanasopoulos, G., & Weatherburn, D. (2018). Forecasting male and female inmate numbers: A comparison of ARIMA and ETS modelling results (Crime and Justice Bulletin No. 219).
  26. Chainey, S., & Ratcliffe, J. (2005). GIS and crime mapping. John Wiley & Sons. https://doi.org/10.1002/9781118685181
  27. Lau, H., Tsang, Y. P., Nakandala, D., & Lee, C. K. M. (2021). Risk quantification in cold chain management: A federated learning-enabled multi-criteria decision-making methodology. Industrial Management & Data Systems. https://doi.org/10.1108/IMDS-04-2020-0199