PSYCHOLOGY WITH SOFT COMPUTING METHOD: FORECASTING OF ANGER EXPRESSION OF THE HUMAN USING THE DEVELOPED MODEL BASED ON SUPPORT VECTOR MACHINE

Anger is a natural emotion that activates self-defense mechanisms to protect oneself in stressful situations. However, if stress level is excessive, or the intensity, frequency, or duration of anger expression is not controlled, it can have negative effects on one's physical health and cause emotional problems like depression, anxiety, lowered quality of life, and interpersonal problems. The purpose of the present study is to forecast the anger expression from the anger state and trait using the developed model based on support vector machine (SVM) in a group of nonclinical individuals. To this end, 3,443 participants including students (60%), university staff (20%) and hospital staff (20%) are examined. After removing the missing data (443 participants), 3,000 data were considered in the analysis. The distribution of gender in the present study was 48% males and 52% females. The mean age of participants was 35.42 years (SD = 8.41, range 18-60 years). The proposed model is a discriminative classifier formally defined by a separating hyperplane. In other words, given labeled training data (supervised learning), the algorithm outputs an optimal hyperplane which categorizes new examples. In the developed model, the training step is performed using a series of data through the known input and output data, and after the validation and testing steps, unknown output data corresponding to the known input data are predicted. The state, feeling, verbal, physical, trait, temperament, and reaction of anger are the inputs of the developed model. The anger expression scales including anger expression-out, anger expression-in, anger control-out, anger control-in, and anger index are forecasted as the output data from the developed model. Results indicate that the developed model based on SVM forecasts anger expression with acceptable accuracy. Therefore, it can be used as an appropriate model to predict how to express people's anger with acceptable accuracy.