Open Access Open Access  Restricted Access Subscription or Fee Access

Machine Learning Mechanism for Adaptive Tourist Recommendation Using Bayesian Algorithm

Pijitra Jomsri, Worasit Choochaiwattana

Abstract



Currently, recommender systems are available in many daily activities such as online shopping search, and social networks. Due to the increasing demand of the tourism industry through information technology, the recommender systems are integrated into the tourism website. This research aims at exploiting user data to recommend tourist attractions by arranging the attractions together with tourism-related information and making recommendations based on information relevant to the needs of each user. The proposed mechanism has an advantage as it can suggest information at the beginning of use without the need for usage history, rankings, and other special knowledge. Thus, new travelers can get recommendations when start using the recommender system. This research focuses on recommending tourist destinations in Thailand using machine learning methods based on Bayesian Personalized Ranking to predict tourist attraction rankings by comparing four methods: 1) Collaborative Filtering Only, 2) Demographic Filtering Only, 3) Collaborative Filtering and Demographic Filtering, and 4) Hybrid Method of Demographic Filtering and Demographic Filtering Combining with Tourist Attraction Category. The experimental results show that the hybrid method of collaborative filtering and demographic filtering combining with the ranking of tourist attractions recommends tourist attractions better than other methods. Therefore, this hybrid model can be used as a model to support the Recommender system of tourism.

Keywords


Machine Learning, Bayesian Personalized Ranking, Tourist Recommendation, Recommender System.

Full Text:

PDF


Disclaimer/Regarding indexing issue:

We have provided the online access of all issues and papers to the indexing agencies (as given on journal web site). It’s depend on indexing agencies when, how and what manner they can index or not. Hence, we like to inform that on the basis of earlier indexing, we can’t predict the today or future indexing policy of third party (i.e. indexing agencies) as they have right to discontinue any journal at any time without prior information to the journal. So, please neither sends any question nor expects any answer from us on the behalf of third party i.e. indexing agencies.Hence, we will not issue any certificate or letter for indexing issue. Our role is just to provide the online access to them. So we do properly this and one can visit indexing agencies website to get the authentic information. Also: DOI is paid service which provided by a third party. We never mentioned that we go for this for our any journal. However, journal have no objection if author go directly for this paid DOI service.