Hybrid geo-semantic model for tourist accommodation recommendation based on web scraping and unsupervised evaluation
Introduction: This article is the result of research on the Tourist Accommodation Recommendation Model Using Machine Learning with Information Extraction Through the Web Scraping Technique conducted at the Universidad Distrital Francisco José de Caldas in 2026.
Problem: In tourism cold-start scenarios, the lack of structured data and user history reduces the quality of accommodation recommendations. Web Scraping is required [2], but it introduces inconsistencies and structural variability that hinder accurate recommendations.
Objective: To design and evaluate a hybrid geo-semantic recommender system that integrates content-based similarity between accommodations with geographic proximity under an unsupervised framework using web-scraped data.
Methodology: Data from 13,204 Colombian accommodations were scraped from Booking.com using Playwright, preprocessed, and represented as vectors. Then, cosine similarity and Haversine distance were combined into a weighted hybrid scoring function, evaluated through similarity standard deviation, intra-list similarity, and geographic relevance.
Results: The base model achieved an average cosine similarity of 0.868 and a mean geographic distance of 0.16 km, with 100% of recommendations within the defined geographic constraint radius. In an exploratory comparison against Booking.com, the proposed model returned semantically and spatially consistent alternatives independent of commercial positioning criteria.
Conclusions: The geo-semantic model generates coherent and geographically relevant recommendations from web-scraped data in cold-start contexts where user interaction data are unavailable.
Originality: This work proposes a reproducible geo-semantic recommender model for tourist accommodation in cold-start scenarios, integrating semantically represented web-scraped accommodation data with geographic proximity to generate recommendations.
Limitations: The model does not incorporate user preference data.
How to Cite
License
Copyright (c) 2026 Ingeniería Solidaria
This work is licensed under a Creative Commons Attribution 4.0 International License.
Cession of rights and ethical commitment
As the author of the article, I declare that is an original unpublished work exclusively created by me, that it has not been submitted for simultaneous evaluation by another publication and that there is no impediment of any kind for concession of the rights provided for in this contract.
In this sense, I am committed to await the result of the evaluation by the journal Ingeniería Solidaría before considering its submission to another medium; in case the response by that publication is positive, additionally, I am committed to respond for any action involving claims, plagiarism or any other kind of claim that could be made by third parties.
At the same time, as the author or co-author, I declare that I am completely in agreement with the conditions presented in this work and that I cede all patrimonial rights, in other words, regarding reproduction, public communication, distribution, dissemination, transformation, making it available and all forms of exploitation of the work using any medium or procedure, during the term of the legal protection of the work and in every country in the world, to the Universidad Cooperativa de Colombia Press.
[1] J. Neidhardt, W. Wörndl, T. Kuflik, D. Goldenberg, and M. Zanker, “Workshop on Recommenders in Tourism (RecTour),” in Proc. 16th ACM Conference on Recommender Systems (RecSys), Seattle, WA, USA, Sep. 2022, pp. 678–679, doi: https://doi.org/10.1145/3523227.3547416. DOI: https://doi.org/10.1145/3523227.3547416
[2] V. Krotov, L. Johnson, and L. Silva, “Legality and ethics of web scraping,” Communications of the Association for Information Systems, vol. 47, Art. no. 24, pp. 539–563, 2020, doi: https://doi.org/10.17705/1CAIS.04724. DOI: https://doi.org/10.17705/1CAIS.04724
[3] S. Guardia, “Ensaio sobre destinos turísticos inteligentes,” Journal of Tourism & Development, no. 27/28, pp. 1515–1528, 2017, doi: https://doi.org/10.34624/rtd.v1i27/28.9897.
[4] F. O. Isinkaye, Y. O. Folajimi, and B. A. Ojokoh, “Recommendation systems: Principles, methods and evaluation,” Egyptian Informatics Journal, vol. 16, no. 3, pp. 261–273, 2015, doi: https://doi.org/10.1016/j.eij.2015.06.005.
[5] L. Celardo, M. Misuraca, and M. Spano, “Geo-referenced sentiment analysis for tourists’ points of interest: The case of Matera European Capital of Culture,” Rivista Italiana di Economia Demografia e Statistica, vol. 78, no. 2, pp. 103–114, 2024, doi: https://doi.org/10.71014/sieds.v78i2.258. DOI: https://doi.org/10.71014/sieds.v78i2.258
[6] N. Thi Diem Kieu and B. Trong Tien Bao, “Determinants of tourist intentions to use mobile applications for accommodation booking: Insights from Ho Chi Minh City,” Journal of Tourism & Development, no. 49, pp. 141–170, 2025, doi: https://doi.org/10.34624/rtd.v49i0.37828.
[7] M. Sumardi, Jufery, Frenky, R. Wongso, and F. A. Luwinda, “‘tripBuddy’ travel planner with recommendation based on user’s browsing behaviour,” Procedia Computer Science, vol. 116, pp. 326–333, 2017, doi: https://doi.org/10.1016/j.procs.2017.10.084. DOI: https://doi.org/10.1016/j.procs.2017.10.084
[8] T. Bomatpalli, “A survey of travel recommender system,” International Journal of Computer Sciences and Engineering, vol. 7, no. 3, pp. 356–362, 2019, doi: https://doi.org/10.26438/ijcse/v7i3.356362. DOI: https://doi.org/10.26438/ijcse/v7i3.356362
[9] J. Borràs, A. Moreno, and A. Valls, “Intelligent tourism recommender systems: A survey,” Expert Systems with Applications, vol. 41, no. 16, pp. 7370–7389, 2014, doi: https://doi.org/10.1016/j.eswa.2014.06.007. DOI: https://doi.org/10.1016/j.eswa.2014.06.007
[10] M. K. Najafabadi, A. H. Mohamed, and M. N. Mahrin, “A survey on data mining techniques in recommender systems,” Soft Computing, vol. 23, no. 2, pp. 627–654, 2019, doi: https://doi.org/10.1007/s00500-017-2918-7. DOI: https://doi.org/10.1007/s00500-017-2918-7
[11] O. A. S. Ibrahim, E. M. G. Younis, E. A. Mohamed, and W. N. Ismail, “Revisiting recommender systems: An investigative survey,” Neural Computing and Applications, 2025, doi: https://doi.org/10.1007/s00521-024-10828-5. DOI: https://doi.org/10.1007/s00521-024-10828-5
[12] A. Cavallo, “Scraped data and sticky prices,” Review of Economics and Statistics, vol. 100, no. 1, pp. 105–119, 2018, doi: https://doi.org/10.1162/REST_a_00652. DOI: https://doi.org/10.1162/REST_a_00652
[13] R. N. Landers, R. C. Brusso, K. J. Cavanaugh, and A. B. Collmus, “A primer on theory-driven web scraping: Automatic extraction of big data from the internet for use in psychological research,” Psychological Methods, vol. 21, no. 4, pp. 475–492, 2016, doi: https://doi.org/10.1037/met0000081. DOI: https://doi.org/10.1037/met0000081
[14] D. Kaur, S. Khanna, and D. Aulakh, “A collaborative location-based travel recommendation system through enhanced rating prediction for the group of users,” Structural Chemistry, vol. 24, no. 1, pp. 357–367, 2013, doi: https://doi.org/10.1007/s11224-012-0084-1. (SD: verificar correspondencia entre revista, título y DOI).
[15] F. O. Isinkaye, Y. O. Folajimi, and B. A. Ojokoh, “Recommendation systems: Principles, methods and evaluation,” Egyptian Informatics Journal, vol. 16, no. 3, pp. 261–273, 2015, doi: https://doi.org/10.1016/j.eij.2015.06.005. DOI: https://doi.org/10.1016/j.eij.2015.06.005
[16] E. Zangerle and C. Bauer, “Evaluating recommender systems: Survey and framework,” ACM Computing Surveys, vol. 55, no. 8, pp. 1–38, 2023, doi: https://doi.org/10.1145/3556536.v DOI: https://doi.org/10.1145/3556536
[17] A. Solano-Barliza et al., “Recommender systems applied to the tourism industry: A literature review,” Cogent Business & Management, vol. 11, no. 1, 2024, doi: https://doi.org/10.1080/23311975.2024.2367088. DOI: https://doi.org/10.1080/23311975.2024.2367088
[18] C. Troussas, A. Krouska, P. Tselenti, D. K. Kardaras, and S. Barbounaki, “Enhancing personalized educational content recommendation through cosine similarity-based knowledge graphs and contextual signals,” Information, vol. 14, no. 9, Art. no. 505, 2023, doi: https://doi.org/10.3390/info14090505. DOI: https://doi.org/10.3390/info14090505
[19] H. Simanjuntak, D. Tarigan, I. Sibarani, C. J. Hutapea, R. Lumbantoruan, and M. Sigiro, “Weighted hybrid recommendation system for Toba tourism based on Google Review data,” in Proc. IEEE International Conference of Computer Science and Information Technology (ICOSNIKOM), Medan, Indonesia, Oct. 2022, pp. 1–8, doi: https://doi.org/10.1109/ICOSNIKOM56551.2022.10034911. DOI: https://doi.org/10.1109/ICOSNIKOM56551.2022.10034911
[20] I. Y. Choi, J. K. Kim, and Y. U. Ryu, “A two-tiered recommender system for tourism product recommendations,” in Proc. Annual Hawaii International Conference on System Sciences (HICSS), Kauai, HI, USA, 2015, pp. 3354–3363, doi: https://doi.org/10.1109/HICSS.2015.405. DOI: https://doi.org/10.1109/HICSS.2015.405
[21] N. Wijaya and A. Furqan, “Coastal tourism and climate-related disasters in an archipelago country of Indonesia: Tourists’ perspective,” Procedia Engineering, vol. 212, pp. 535–542, 2018, doi: https://doi.org/10.1016/j.proeng.2018.01.069. DOI: https://doi.org/10.1016/j.proeng.2018.01.069
[22] A. Umanets, A. Ferreira, and N. Leite, “GuideMe – A tourist guide with a recommender system and social interaction,” Procedia Technology, vol. 17, pp. 407–414, 2014, doi: https://doi.org/10.1016/j.protcy.2014.10.248. DOI: https://doi.org/10.1016/j.protcy.2014.10.248
[23] T. Izumi, T. Kitamura, and Y. Nakatani, “A suggestive recommendation method to make tourists ‘feel like going,’” IFAC-PapersOnLine, vol. 49, no. 19, pp. 573–578, 2016, doi: https://doi.org/10.1016/j.ifacol.2016.10.606. DOI: https://doi.org/10.1016/j.ifacol.2016.10.606
[24] M. E. B. H. Kbaier, H. Masri, and S. Krichen, “A personalized hybrid tourism recommender system,” in Proc. IEEE/ACS 14th International Conference on Computer Systems and Applications (AICCSA), Hammamet, Tunisia, 2017, pp. 244–250, doi: https://doi.org/10.1109/AICCSA.2017.12. DOI: https://doi.org/10.1109/AICCSA.2017.12
[25] J. D. C. L. Soares, Suyoto, and A. J. Santoso, “M-guide: Hybrid recommender system tourism in East Timor,” in Proc. International Conference on Soft Computing, Intelligent System and Information Technology (ICSIIT), Bali, Indonesia, 2017, pp. 303–309, doi: https://doi.org/10.1109/ICSIIT.2017.16. DOI: https://doi.org/10.1109/ICSIIT.2017.16
[26] C. S. Wang, C. Y. Li, and C. C. Yeh, “Intelligence traveling schedule recommender based on commonsense reasoning algorithm,” in Proc. International Conference on Computer and Communication Engineering (ICCCE), Kuala Lumpur, Malaysia, 2010, pp. 1–5, doi: https://doi.org/10.1109/ICCCE.2010.5556814. DOI: https://doi.org/10.1109/ICCCE.2010.5556814
[27] G. Hirakawa, G. Satoh, K. Hisazumi, and Y. Shibata, “Data gathering system for recommender system in tourism,” in Proc. 18th International Conference on Network-Based Information Systems (NBiS), Taipei, Taiwan, 2015, pp. 521–525, doi: https://doi.org/10.1109/NBiS.2015.78. DOI: https://doi.org/10.1109/NBiS.2015.78
[28] V. Subramaniyaswamy, V. Vijayakumar, R. Logesh, and V. Indragandhi, “Intelligent travel recommendation system by mining attributes from community contributed photos,” Procedia Computer Science, vol. 50, pp. 447–455, 2015, doi: https://doi.org/10.1016/j.procs.2015.04.014. DOI: https://doi.org/10.1016/j.procs.2015.04.014
[29] Q. Liu, E. Chen, H. Xiong, Y. Ge, Z. Li, and X. Wu, “A cocktail approach for travel package recommendation,” IEEE Transactions on Knowledge and Data Engineering, vol. 26, no. 2, pp. 278–293, 2014, doi: https://doi.org/10.1109/TKDE.2012.233. DOI: https://doi.org/10.1109/TKDE.2012.233
[30] L. T. Yong, “A collaborative awareness framework for mobile tourist recommender system,” in Proc. 3rd International Conference on Computer Research and Development (ICCRD), Shanghai, China, 2011, pp. 329–333, doi: https://doi.org/10.1109/ICCRD.2011.5764030. DOI: https://doi.org/10.1109/ICCRD.2011.5764030
[31] E. Ashley-Dejo, S. M. Ngwira, and T. Zuva, “A context-aware proactive recommender system for tourist,” in Proc. 3rd International Conference on Advances in Computing, Communication and Engineering (ICACCE), Durban, South Africa, 2016, pp. 271–275, doi: https://doi.org/10.1109/ICACCE.2016.8073760. DOI: https://doi.org/10.1109/ICACCE.2016.8073760
[32] A. Kumar, S. Gupta, S. K. Singh, and K. K. Shukla, “Comparison of various metrics used in collaborative filtering for recommendation system,” in Proc. 8th International Conference on Contemporary Computing (IC3), Noida, India, 2015, pp. 150–154, doi: https://doi.org/10.1109/IC3.2015.7346670. DOI: https://doi.org/10.1109/IC3.2015.7346670
[33] E. Cavenaghi, L. Camaione, P. Minasi, G. Sottocornola, F. Stella, and M. Zanker, “A re-rank algorithm for online hotel search,” in Springer Proceedings in Business and Economics, Cham, Switzerland: Springer Nature Switzerland, 2023, pp. 53–64, doi: https://doi.org/10.1007/978-3-031-25752-0_5. DOI: https://doi.org/10.1007/978-3-031-25752-0_5
[34] H. Hu and X. Zhou, “Recommendation of tourist attractions based on Slope One algorithm,” in Proc. 9th International Conference on Intelligent Human-Machine Systems and Cybernetics (IHMSC), Hangzhou, China, 2017, vol. 1, pp. 418–421, doi: https://doi.org/10.1109/IHMSC.2017.102. DOI: https://doi.org/10.1109/IHMSC.2017.102
[35] J. Ghahramani, M. Sadeghzadeh, and A. Broumandnia, “A hybrid location-based recommender system for trip planning and mobility using geo-tagged media,” Journal of Intelligent Information Systems, 2025, doi: https://doi.org/10.1007/s10844-025-00992-y. DOI: https://doi.org/10.1007/s10844-025-00992-y
[36] F. Majeed, A. Siddique, M. Zafar, and K. Shaukat, “A fusion of recommendation techniques to deliver personalized tourism experience,” IET Software, vol. 20, no. 1, 2026, doi: https://doi.org/10.1049/sfw2.9218059. DOI: https://doi.org/10.1049/sfw2/9218059
[37] D. M. G. Muñoz, J. D. C. Bernal, and J. I. R. Molano, “Machine learning applications in tourism: Case study from Colombia and its post-conflict areas,” Journal of Tourism & Development, no. 40, pp. 93–102, 2023. (SD: el DOI https://doi.org/10.23919/CISTI58278.2023.10211549 corresponde a una ponencia CISTI y no a este artículo de revista).
[38] N. Luh Putu Melya Wati, I. Made Dwi Putra Asana, N. Wayan Suardiati Putri, K. Jaya Atmaja, and I. Gede Iwan Sudipa, “Comparison of automation testing on card printer project using Playwright and Selenium tools,” Computing, Networking, Architecture, and High Performance Computing, vol. 6, no. 3, 2024, doi: https://doi.org/10.47709/cnahpc.v6i3.4362. DOI: https://doi.org/10.47709/cnahpc.v6i3.4362
[39] A. Jadon and A. Patil, “A comprehensive survey of evaluation techniques for recommendation systems,” in Artificial Intelligence and Machine Learning for Recommendation Systems, Cham, Switzerland: Springer Nature Switzerland, 2025, pp. 281–304, doi: https://doi.org/10.1007/978-3-031-71484-9_25. DOI: https://doi.org/10.1007/978-3-031-71484-9_25
[40] Z. Shen, “Outlier detect using vector cosine similarity by adding a dimension,” in Proc. International Conference on Artificial Intelligence in Information and Communication (ICAIIC), Osaka, Japan, Feb. 2024, pp. 255–259, doi: https://doi.org/10.1109/ICAIIC60209.2024.10463442. DOI: https://doi.org/10.1109/ICAIIC60209.2024.10463442
[41] J. M. Luna, “Introduction to data mining,” in Periodic Pattern Mining, vol. 2, Singapore: Springer Singapore, 2021, pp. 1–22, doi: https://doi.org/10.1007/978-981-16-3964-7_1. DOI: https://doi.org/10.1007/978-981-16-3964-7_1
[42] Z. Arifin, M. R. Ibrahim, and H. R. Hatta, “Nearest tourism site searching using Haversine method,” in Proc. 3rd International Conference on Information Technology, Computer, and Electrical Engineering (ICITACEE), Semarang, Indonesia, 2016, pp. 293–296, doi: https://doi.org/10.1109/ICITACEE.2016.7892458. DOI: https://doi.org/10.1109/ICITACEE.2016.7892458
[43] A. Vulevic, S. Roy, R. Alexandre Castanho, M. Franco, and G. Couto, “Exploring the geo-tourism potential and its accessibility in Danube Region, Serbia: A geo-statistical approach,” in Urban Agglomeration – Extracting Lessons for Sustainable Development. London, U.K.: IntechOpen, 2024, doi: https://doi.org/10.5772/intechopen.1004744. DOI: https://doi.org/10.5772/intechopen.1004744
[44] M. Garramone and M. Scaioni, “Adapting the ‘15-minute city’ concept to medium-sized urban contexts: A case study in Desio, Italy,” Regional Science Policy & Practice, vol. 18, no. 3, Art. no. 100283, 2026, doi: https://doi.org/10.1016/j.rspp.2026.100283. DOI: https://doi.org/10.1016/j.rspp.2026.100283
[45] S. V. Madangarli, G. Suganeshwari, S. P. Syed Ibrahim, M. S. Kavitha, and N. Setozaki, “Semantic and temporal-aware hybrid embedding for transformer-based sequential recommendation,” Artificial Intelligence Review, vol. 59, no. 4, Art. no. 110, 2026, doi: https://doi.org/10.1007/s10462-025-11483-5. DOI: https://doi.org/10.1007/s10462-025-11483-5
[46] F. Ricci, L. Rokach, B. Shapira, and P. B. Kantor, Eds., Recommender Systems Handbook. New York, NY, USA: Springer, 2011, doi: https://doi.org/10.1007/978-0-387-85820-3. DOI: https://doi.org/10.1007/978-0-387-85820-3
[47] R. Burke, “Evaluating the dynamic properties of recommendation algorithms,” in Proc. 4th ACM Conference on Recommender Systems (RecSys), Barcelona, Spain, 2010, pp. 225–228, doi: https://doi.org/10.1145/1864708.1864753. DOI: https://doi.org/10.1145/1864708.1864753
[48] R. Cañamares, P. Castells, and A. Moffat, “Offline evaluation options for recommender systems,” Information Retrieval Journal, vol. 23, no. 4, pp. 387–410, 2020, doi: https://doi.org/10.1007/s10791-020-09371-3. DOI: https://doi.org/10.1007/s10791-020-09371-3
[49] M. Jesse, C. Bauer, and D. Jannach, “Intra-list similarity and human diversity perceptions of recommendations: The details matter,” User Modeling and User-Adapted Interaction, vol. 33, no. 4, pp. 769–802, 2023, doi: https://doi.org/10.1007/s11257-022-09351-w. DOI: https://doi.org/10.1007/s11257-022-09351-w
[50] S. Marukatat, “Tutorial on PCA and approximate PCA and approximate kernel PCA,” Artificial Intelligence Review, vol. 56, no. 6, pp. 5445–5477, 2023, doi: https://doi.org/10.1007/s10462-022-10297-z. DOI: https://doi.org/10.1007/s10462-022-10297-z
[51] G. Sidorov, A. Gelbukh, H. Gómez-Adorno, and D. Pinto, “Soft similarity and soft cosine measure: Similarity of features in vector space model,” Computación y Sistemas, vol. 18, no. 3, pp. 491–504, 2014, doi: https://doi.org/10.13053/CyS-18-3-2043. DOI: https://doi.org/10.13053/cys-18-3-2043
[52] M. Rafiq, Y. S. Chauhan, and S. Sahay, “Efficient implementation of Mahalanobis distance on ferroelectric FinFET crossbar for outlier detection,” IEEE Journal of the Electron Devices Society, vol. 12, pp. 516–524, 2024, doi: https://doi.org/10.1109/JEDS.2024.3416441. DOI: https://doi.org/10.1109/JEDS.2024.3416441
