A qualitative attraction ranking model for personalized recommendations

Abstract

Purpose This paper aims to find a way to personalize attraction recommendations for travelers. The research objective is to find a more accurate way to suggest new attractions to each traveler based on the opinions of other like-minded travelers and the traveler’s preferences. Design/methodology/approach To achieve the goal, developers have created a personalized system to generate attraction recommendations. The system considers an individual traveler’s preferences to construct a qualitative attraction ranking model. The new ranking model is the result of blending two processes: K-means clustering and the analytic hierarchy process (AHP). Findings The performance of the developed recommendation system has been assessed by measuring the accuracy and scalability of the ranking model of the system. The experimental results indicate that the ranking model always returns accurate results independent of the number of attractions and the number of travelers in each cluster. The ranking model has also proved to be scalable because the processing time is independent of the numbers of travelers. Additionally, the results reveal that the overall system usability is at a very satisfactory level. Research limitations/implications The main theoretical implication is that integrating the processes of K-means and AHP techniques enables a new qualitative ranking model for personalized recommendations that deliver only high-quality attractions. However, the designed recommendation system has some limitations. First, it is necessary to manually update information about the new tourist attractions. Second, the overall response time depends on the internet bandwidth and latency. Practical implications This research contributes to the tourism business and individual travelers by introducing an accurate and scalable way to suggest new attractions to each traveler. The potential benefit includes possible increased revenue for travel agencies that offer personalized package tours and support individual travelers to make the final travel decisions. The designed system could also integrate with itinerary planning systems to plot out a journey that pinpoints what travelers will most enjoy. Originality/value This research proposes a design and implementation of a personalized recommendation system based on the qualitative attraction ranking model introduced in this article. The novel ranking model is designed and developed by integrating K-means and AHP techniques, which has proved to be accurate and scalable.

Personalized Tourism Recommendations and the E-Tourism User Experience

“…Personalized Tourism Recommendations (PTR). Collating the existing literature, we have categorized personalized tourism recommendations into six types: (1) personalized attraction recommendations, which provide a rated list of attractions (Angskun & Angskun, 2018); (2) personalized travel route recommendations, which combine user behavior habits, interest preferences, and route popularity (Fan & Zhang, 2022); (3) comprehensive user-adapted travel planning recommendations, which integrate travel schedules, tourist attractions visited, local hotel selection, and travel budget calculation (Chiang & Huang, 2015); (4) personalized hotel recommendations, which combine user characteristics and their personalized preferences with public preferences (K. Chen, Wang, & Zhang, 2021);…”

“…Collating the existing literature, we have categorized personalized tourism recommendations into six types: (1) personalized attraction recommendations, which provide a rated list of attractions (Angskun & Angskun, 2018); (2) personalized travel route recommendations, which combine user behavior habits, interest preferences, and route popularity (Fan & Zhang, 2022); (3) comprehensive user-adapted travel planning recommendations, which integrate travel schedules, tourist attractions visited, local hotel selection, and travel budget calculation (Chiang & Huang, 2015); (4) personalized hotel recommendations, which combine user characteristics and their personalized preferences with public preferences (K. Chen, Wang, & Zhang, 2021); (5) personalized online booking recommendations, which integrate the identification of online opinion experts, construction of social networks, detection of user communities, and interaction of PTRs (Chang et al, 2022); and (6) personalized travel package recommendations, which produce dynamic suggestions for users based on geo-tagged photos, taking into consideration multidimensional data such as time, location, implicit ratings, tourist characteristics, and their sequential travel patterns (Kolahkaj et al, 2020).…”

Research on data mining and the short video platforms users' personalized information needs

“…The purpose of cluster analysis distinction and classification analysis is to reasonably divide the input unscaled records according to certain rules, so as to achieve the effect of making the difference between groups as large as possible and the difference within the group as small as possible [9]. The K-means algorithm is a commonly used algorithm for clustering in data mining, which divides the data into predetermined K classes based on the minimization error function.…”

Online Environmental Reporting: Does Ownership Structure Matter?

“…For instance, Al-Tuwaijri et al (2003) and Muhammad et al, (2015) found a substantial connection between both environmental and financial performance. Under this pressure, corporations have to publish their environmental activities in their financial reports (Walden and Schwartz, 1997), and as the paperbased report is costly with limited space, corporations found the Internet as an efficient alternative tool that allows them to capitalize on its attributes such as unlimited space (Angskun and Angskun, 2008), widespread and accessibility (Huber, & Vitouch, 2008), timely and up-to-date information (Joshi and Jawaher, 2003;Adham and Ahmed, 2005), supporting different types of presentation such as powerful hypertext as well as hypermedia (Xiao et al, 2005), and low cost (Hassan, 2014). Malaysia is an emerging market country and a rapidly industrializing economy.…”