Tourism Recommendation based on Word Embedding from Card Transaction Data

Minsung Hong1, Namho Chung2 and Chulmo Koo2

  1. Smart Tourism Research Center, Kyung-Hee University
    26-6, Kyungheedae-ro, Dongdaemun-gu, Seoul, South Korea
    {mshong.res}@gmail.com
  2. Smart Tourism Education Platform, Kyung-Hee University
    26-6, Kyungheedae-ro, Dongdaemun-gu, Seoul, South Korea
    nhchung, helmetgu}@hku.ac.kr

Abstract

In the tourism industry, millions of card transactions generate a massive volume of big data. The card transactions eventually reflect customers’ consumption behaviors and patterns. Additionally, recommender systems that incorporate users’ personal preferences and consumption is an important subject of smart tourism. However, challenges exist such as handling the absence of rating data and considering spatial factor that significantly affects recommendation performance. This paper applies well-known Doc2Vec techniques to the tourism recommendation. We use them on non-textual features, card transaction dataset, to recommend tourism business services to target user groups who visit a specific location while addressing the challenges above. For the experiments, a card transaction dataset among eight years from Shinhan, which is one of the major card companies in the Republic of Korea, is used. The results demonstrate that the use of vector space representations trained by the Doc2Vec techniques considering spatial information is promising for tourism recommendations.

Key words

recommender system, word embedding, neural networks, smart tourism

Digital Object Identifier (DOI)

https://doi.org/10.2298/CSIS220620002H

Publication information

Volume 20, Issue 3 (June 2023)
Year of Publication: 2023
ISSN: 2406-1018 (Online)
Publisher: ComSIS Consortium

Full text

DownloadAvailable in PDF
Portable Document Format

How to cite

Hong, M., Chung, N., Koo, C.: Tourism Recommendation based on Word Embedding from Card Transaction Data. Computer Science and Information Systems, Vol. 20, No. 3, 911–931. (2023), https://doi.org/10.2298/CSIS220620002H