Title: Investigating the key factors for socially excluded groups in college

Authors: Hongying Sun; Aishi Liang; Peiqin Zhang; Wei Zheng

Addresses: College of Computational Science, Zhongkai University of Agriculture and Engineering, Guangzhou 510225, China; School of Business, Sun Yat-sen University, Guangzhou 510275, China ' College of Computational Science, Zhongkai University of Agriculture and Engineering, Guangzhou 510225, China ' McCoy College of Business Administration, Texas State University, 601 University Drive, San Marcos, TX 78666, USA ' College of Computational Science, Zhongkai University of Agriculture and Engineering, Guangzhou 510225, China

Abstract: This paper aims to identify the key factors that are essential to the behaviour and life of socially excluded groups in colleges. We first conduct a questionnaire filled by undergraduate students from different colleges in China. Then the data collected by the questionnaire was studied by descriptive analysis, chi-square test and correlation analysis on the relationships between the seven key factors and three aspects. For better understanding, the distribution of socially excluded groups, we propose a self-organising artificial neural network model to cluster and analyse the proportion of socially excluded group and non-socially excluded group based on the seven factors. We find that the rate of social exclusion in college is about 18%. This paper offers an analytical method to determine whether a student is socially excluded or not in college by measuring the key factors of the social exclusion of campus life.

Keywords: socially excluded group; chi-square test and correlation analysis; self-organising artificial neural network model; cluster.

DOI: 10.1504/IJHES.2017.088007

International Journal of Higher Education and Sustainability, 2017 Vol.1 No.3, pp.183 - 205

Received: 01 Jul 2016
Accepted: 01 Nov 2016
Published online: 14 Nov 2017 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article