A Framework for Determining the Big Five Personality Traits Using Machine Learning Classification through Graphology

Along with the progress of times, development graphology has changed towards computerization. The fundamental problem in automated is how to determine personality traits through digital handwriting using principles graphology. Although various models and approaches have been developed research related graphology, there are still obstacles overcome such as selection preprocessing techniques image processing algorithms extract features proper classification get maximum accuracy. Therefore, this study aims design a reliable framework machine learning filtering, thresholding, normalization features. Then, classified according Big Five model. Experiments decision tree, SVM (kernel RBF), KNN produced an accuracy above 99%. These results indicated that proposed can be well applied predict model analysis