Matching of compatible different attributes for compatibility of members and groups

Abstract

The compatibility of members and groups requires the appropriate matching method which depends on the level of attitudes toward the components of the mentoring system. Generally, the mentoring system consists of two roles, including the mentor and the mentee. Identifying these compatible roles in an online community is challenging. This paper proposes a matching model for classifying the compatibility of mentors and mentees in a large group of members by using compatible different attributes, which consist of 24 attributes of attitude towards similarities and dissimilarities attributes between those two roles. The data was collected from 32 mentors and 205 mentees at four universities including Mae Fah Luang University, University of Phayao, Chiang Rai Rajabhat University, and Rajabhat Maha Sarakham University. The collected data was classified by two primary classifiers, k-means and k-medoids, to compare the classification results. Overall, the comparison results showed that k-medoids provided better classification results than k-means.