search for


The tourist recommendation algorithm considering weather and popularity in Gyeongbuk
Journal of the Korean Data & Information Science Society 2022;33:845-56
Published online September 30, 2022;
© 2022 Korean Data and Information Science Society.

Seo Yun Am1 · Kim Heesoo2 · Yoon Sanghoo3

1Department of Data Science, Jeju National University
23Division of Mathematics and Data Science, Daegu University
3Department of Data Science, Daegu University
Correspondence to: 1 Assistant professor, Department of Data Science, Jeju National University, Jeju Special Self-Governing Province, 63423, Korea.
2 Undergraduate, Department of Data Science, Daegu University, Daegu 38453.
3 Associate professor, Department of Data Science, Daegu University, Daegu 38453, Korea. E-mail:
This is an Open Access article distributed under the terms of the Creative Commons Attribution Non-Commercial License ( which permits unrestricted non-commercial use, distribution, and reproduction in any medium, provided the original work is properly cited.
The weather has a lot of influence on itinerary decisions. The combination of weather and tourism data can create new values. This study proposes a recommendation algorithm for tourist attractions in North Gyeongsang Province considering the Korean-style tourism climate index and the popularity of tourist attractions according to weather conditions. First, the popularity of tourist attractions was obtained by using the number of reviews, ratings, and blogs provided by Naver. In addition, we obtain optimized popularity scores compared to the number of monthly tourist searches provided by Korea Datalab. Afterward, thermal comfort, wind speed, precipitation, and sunshine hours of tourist attractions are used to generate tourist climate indices. The weather information of tourist attractions was used to predict the weather conditions of the Korea Meteorological Administration’s weather station and the latitude and longitude of tourist attractions using the kriging technique. Calculating the Korean-style Tourism Climate Index (KTCI) of tourist attractions through the predicted weather information can quantitatively evaluate the impact of weather conditions on tourism. A tourist recommendation algorithm was developed to reflect the KTCI score in the popularity of the finally optimized tourist attractions in Gyeongbuk. As a result of this study, there is a difference between sunny and cloudy days, but it does not have a significant impact on tourist recommendations and is similar to the ranking considering only popularity. On rainy days, recommendations focused on indoor tourist attractions with less outdoor exposure were prioritized.
Keywords : Kriging, Korean tourism climate index, optimization, tourism popularity, weather.