Study on cluster analysis characteristics and classification capabilities — a case study of satisfaction regarding hotels and bed & breakfasts of Chinese tourists in Taiwan. Issue 1 (2nd January 2017)

• Record Type: Journal Article
• Authors: Tsang, Seng-Su; Wang, Wen-Cheng; Ku, Hao-Hsiang
• Is Part Of: Intelligent automation & soft computing. Volume 23:Issue 1(2017)
• Page Start: 103
• Page End: 108
• Publication Date: 2017-01-02
• Subjects: Cluster analysis -- Kmeans -- Kmedoid -- FCM Cluster -- GK Cluster; Artificial intelligence -- Periodicals; Intelligent control systems -- Periodicals; 003.5
• DOI: 10.1080/10798587.2016.1139285
• Languages: English
• ISSNs: 1079-8587

Abstract

Abstract: Cluster analysis is a multivariate statistical analysis method for the classification of samples based on the principle of "like attracts like". It requires reasonable classification according to the characteristics in a reasonable manner, and without any mode for reference, in other words, classification is implemented without any prior knowledge. It has been applied in many aspects. In this paper, four cluster analysis methods are used to study the questionnaire data of Chinese tourists' satisfaction regarding Taiwan's hotels and Bed & Breakfasts, (B&Bs). First, this study applied principal component analysis in reducing questionnaire variables, and then gray relational analysis to assess the overall satisfaction performance. By sorting the overall satisfaction performance values, the performance values combined with the principle components were used as the testing sample data. Afterwards, the samples were categorized into three categories and four categories according to performance value. The four cluster analysis methods were used for clustering the principle components in order to observe their cluster performance and classification capabilities. The testing data testing results suggested that GK Cluster can obtain good cluster performance and good classification capabilities.