Paper Title
Stress Prediction using an Efficient Psychological Question Mining Method

Abstract
Stress questionnaire are becoming increasingly important for measuring psychological stress that was designed to measure the degree to which individuals appraise situations in their lives as stressful. Whichever the use of long psychological questionnaires in this context may be exhaustive under a stressful situation and important with participation in screening. In this study, we propose an efficient method for designing predictors of psychological stress using a small set of psychological question items obtained by using an inheritable bi-objective genetic algorithm (IBCGA) from our dataset which is composed 87 adult without stressful and 83 adult with stressful who responses to the stress scale of 90 questions. For the independent-adult prediction, the training dataset contains 80% adult with and without stressful and other serves as the test dataset. A predictor, PreStress, composed of 5 optimal features selected using IBCGA bases on an intelligent genetic algorithm is created for predicting psychological stress with 100 % training accuracy and the test accuracy is 97%. The web server is available at http://camt.pythonanywhere.com/iPressure. Keywords - Stress Questionnaire, Psychological Stress, Genetic Algorithm, Prediction, SVM.