Classification Algorithms to Predict Students' Extraversion-Introversion Traits

Knowing students' personality traits helps to improve the environment of learning and living in college. However, the questionnaire commonly used for personality prediction has some inherent limitations such as inefficiency and proneness to cheating. In this paper, we propose a novel approach b...

Full description

Saved in:
Bibliographic Details
Published in2016 International Conference on Cyberworlds (CW) pp. 135 - 138
Main Authors Liang Ge, Huang Tang, Qing Zhou, Yunheng Tang, Jiangtao Lang
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.09.2016
Subjects
education data mining
extraversion-introversion
personality
SVM
Online AccessGet full text

Cover

More Information
Summary:Knowing students' personality traits helps to improve the environment of learning and living in college. However, the questionnaire commonly used for personality prediction has some inherent limitations such as inefficiency and proneness to cheating. In this paper, we propose a novel approach based on data mining to determine students' personality traits in particular the extraversion and introversion. Real data set comes from 79 undergraduate students at Chongqing University. We use the results of the Revised Eysenck Personality Questionnaire Short Scale for Chinese (EPQ-RSC) as class labels. Then, three classical classifiers are trained to infer the extraverts and introverts by the features which are extracted from web browsing history and consumption records of campus cards. The experimental results show that the linear SVM performs best with approximate accuracy of 72% and F-measure of 77%. According to our work, it's promising to predict students' extraversion-introversion traits using classification method based on campus data.
DOI:10.1109/CW.2016.27