Context-Aware Recommender System based on Machine Learning in Tourist Mobile Application

  • Nor Liza Saad
  • Nurkhairizan Khairudin
  • Azilawati Azizan
  • Abdullah Sani Abd Rahman
  • Roslina Ibrahim

Abstract

The amount of information available in the World Wide Web has drastically increased nowadays. All this information may be particularly useful for users who plan to visit any places of their interest but a list possibilities search results by the Web search engines will be overwhelming. To decide which options suit to their interest from the long list of options can be tricky and time consuming mainly for Muslim travelers who have a few of religion constraints. The objective of this research is to develop a tourist mobile application that can be incorporated with machine learning based recommender system. For the initial framework, the tourist mobile application prototype was developed based on Penang tourist areas by using Waterfall Model system development approach. The application prototype was evaluated based on usability study as to get insight the users’ acceptance. Furthermore, data were collected simulated based on the mobile application prototype to be used for finding the suitable machine learning algorithms in the recommendation system module. Based on usability study, most users agreed that the tourist mobile application is easier and useful for them. From the machine learning evaluation, Random Forest algorithm has generated the most accurate prediction compared to Decision Tree, Logistic Regression and Generalized Linear Model. This paper provides the fundamental knowledges on machine learning design and evaluation useful in the tourist mobile application with context-aware recommender system.

Published
2022-05-27
How to Cite
SAAD, Nor Liza et al. Context-Aware Recommender System based on Machine Learning in Tourist Mobile Application. Mathematical Sciences and Informatics Journal, [S.l.], v. 3, n. 1, p. 19-28, may 2022. ISSN 2735-0703. Available at: <https://myjms.mohe.gov.my/index.php/mij/article/view/18263>. Date accessed: 07 dec. 2022. doi: https://doi.org/10.24191/mij.v3i1.18263.
Section
Articles

Most read articles by the same author(s)

Obs.: This plugin requires at least one statistics/report plugin to be enabled. If your statistics plugins provide more than one metric then please also select a main metric on the admin's site settings page and/or on the journal manager's settings pages.