A Study of Tourist Attractions Recommendation System in Bangkok for Foreign Tourist

Main Article Content

Phatara Sutrsuwan
Duanpen Teerawanviwat
Pachitjanut Siripanich

Abstract

The objective of this research is to develop personalize recommendation system for foreigners in Bangkok Metropolitan Region by comparing the performance of recommendation system that developed from (1) Popularity based (2) Content-based (3) Collaborative filtering (4) Hybrid model by using travel historical data of foreign tourists that scraped from Tripadvisor, which was the world’s largest travel site. The data was split into training data for 90% and testing data for 10%, which data in the testing set was the latest attractions that each user visited in the past. Then evaluate the performance of each algorithm with mean average precision (MAP) and mean average recall (MAR) in the range of recommended list(k) from 1 to 10. Experimental results demonstrate that the Hybrid model, which uses the weighted-average method gives the best results that have MAP@10 and MAR@10 values of 0.7283 and 0.9659, followed by Content-based which was the best independent algorithm, has MAP@10 and MAR@10 values of 0.6691 and 0.9654, respectively. On the other hand, Collaborative filtering gives the worst results.

Article Details

Section
Research Articles

References

ณิชาภัทร สุรวัฒนานนท์. (2562). การท่องเที่ยวกับบทบาทขับเคลื่อนเศรษฐกิจไทย ฮีโร่จำเป็นหรือ ฮีโร่ตัว จริง?. สืบค้นเมื่อ 17 สิงหาคม 2563, จาก https://www.bot.or.th/Thai/ResearchAndPublications/articles/Pages/Article_29Oct2019.aspx

นัชชา ถิระสาโรช และวิโรจน์ อรุณมานะกุล. (2560). “การศึกษาการแยกนัยความหมายของ หัว ในภาษาไทยโดยใช้วิธีการวิเคราะห์ความหมายแอบแฝง,” (วิทยานิพนธ์ปริญญาดุษฎีบัณฑิต) คณะอักษรศาสตร์ มหาวิทยาลัยจุฬาลงกรณ์, กรุงเทพฯ

พชรพจน์ นันทรามาศ, กิตติพงษ์ เรือนทิพย์, และจารุวรรณ เหล่าสัมฤทธิ์. (2563). เจาะพฤติกรรมท่องเที่ยวใน New Normal: เมื่อโควิดทำชีวิตเปลี่ยน. สืบค้น 24 สิงหาคม 2563, จาก http://krungthai.com/download/economyresources/EconomyResourcesDownload_450เจาะพฤติกรรม ท่องเที่ยวใน New Normal:เมื่อโควิดทำชีวิตเปลี่ยน_31_08_63.pdf

Bruke, R. (2002). Hybrid Recommender Systems: Survey and Experiments. User Model User- Adap Inter, 12(4), 331-370

Badaro, G., Hajj, H., El-Hajj, W., Nachman, L. (2013). A Hybrid Approach with Collaborative Filtering for Recommender Systems. 2013 9th International Wireless Communications and Mobile Computing Conference, IWCMC 2013. 349-354. 10.1109/IWCMC.2013.6583584.

Chujai, P., Singthongchai, J., Yasaga, S., Surattgara, N., and Buranakutti, K. (2020). The Tourist Attractions Recommender System for Bangkok Thailand. Recommender System for Bangkok Thailand, International Journal of Computer Theory and Engineering, 12(1), 22-27

Das, D., Sahoo, L., and Datta, S. (2017). A Survey on Recommendation System. International Journal of Computer Applications, 160(7), 6-10.

Knoema. (2020). Thailand Contribution Of Travel And Tourism To GDP (% Of GDP), 1995-2020. Retrieved August 17, 2020, from https://knoema.com/atlas/Thailand/topics/Tourism/Travel-and-Tourism-Total-Contribution-to-GDP/Contribution-of-travel-and-tourism-to-GDP-percent-of-GDP

Li, G., Hua, J., Yuan, T., Wu, J., Jiang, Z., Zhang, H., and Li, T. (2019). Novel Recommendation System for Tourist Spots Based on Hierarchical Sampling Statistics and SVD++. Mathematical Problems in Engineering, 19, 1-15.

Pourheidari, V., Mollashahi, E. S., Vassileva J., and Deters, R. (2018). "Recommender System based on Extracted Data from Different Social Media. A Study of Twitter and LinkedIn. 2018 IEEE 9th Annual Information Technology, Electronics and Mobile Communication Conference (ICON), Vancouver, 215-222.

Sawtelle, S. (2020). Mean Average Precision (MAP) For Recommender Systems. Retrieved August 24, 2020, from https://sdsawtelle.github.io/blog/output/mean-average-precision-MAP-for-recommender-systems.html

Sarwar, B., Karypis, G., Konstan, J., and Riedl, J. (2001). Incremental singular value decomposition algorithms for highly scalable recommender systems. Proceedings of the 10th international conference on the World Wide Web, 285-295.

Shani, G., Gunawardana A. (2011) Evaluating Recommendation Systems. In: Ricci F., Rokach L., Shapira B., Kantor P. (eds) Recommender Systems Handbook. Springer, Boston, MA. https://doi.org/10.1007/978-0-387-85820-3_8

Taifi, M. (2020). MRR vs MAP NDCG: Rank-Aware Evaluation Metrics and When to Use Them. Retrieved August 17, 2020, from https://medium.com/swlh/rank-aware-recsys-evaluation-metrics-5191bba16832

Translate Thai References

Nantaramat, P., Rueanthip, K. & Laosamrit, J. (2020). Penetrating travel behavior in New Normal: when COVID changes life. Retrieved August 24, 2020, from https://krungthai.com/Download/economyresources/EconomyResourcesDownload_45 0เจาะพฤติกรรมท่องเที่ยวใน_New_Normal_เมื่อโควิดทำชีวิตเปลี่ยน_31_08_63.pdf

Surawattananon, N. (2019). Tourism and its role in driving the Thai economy. Is it a necessary hero or a real hero?. Retrieved August 17, 2020, from https://www.bot.or.th/ThaiResearchAndPublications/articles/Pages/Article_29Oct2019.aspx

Tirasaroj, N. & Arunmanakul, V. (2017). A Study of Word Sense Discrimination of /Hua4/ in Thai Using Latent Semantic Analysis. (Doctoral dissertation) Facalty of Arts, Chulalongkorn University, Bangkok