U.P.B. Sci. Bull., Series C, Vol. 79, Iss. 4, 2017 ISSN 2286-3540 3-LAYER ARCHITECTURE FOR DETERMINING THE PERSONALITY TYPE FROM HANDWRITING ANALYSIS BY COMBINING NEURAL NETWORKS AND SUPPORT VECTOR MACHINES Mihai GAVRILESCU 1 We propose a 3-layer architecture for determining the personality type of a subject by only analyzing handwriting. The proposed architecture combines Neural Network and Support Vector Machine approaches and it is tested in various configurations for determining which combination offers the best personality type classification results for each mixture of handwriting features. In order to test the system, we created a new training database based on Myers-Briggs Type Indicator (MBTI) questionnaire with the purpose of eliminating the inconsistencies of the experimental results compared to manual analysis. We present the architecture, the experimental results, as well as further improvements that could be brought to the current architecture. Keywords: neural networks, affective computing, personality recognition, bioinformatics 1. Introduction Handwriting is one of the most important means of communication present in our lives for centuries. Although it was intensively used, only recently has it been correlated to the personality and emotional state of the writer and this is currently a disputed domain. The current ways of analyzing handwriting are by means of a psychological analysis called graphology. Because it is though that the brain forms characters based on habits of the writer, it is considered that each neurological brain pattern forms a distinctive neuromuscular movement acting the same for individuals with the same type of personality and hence the writing of an individual is an accurate image of a person’s brain [1]. Graphologists typically use different handwriting features in order to study the personality or emotional state of the writer, such features being: weight of the strokes [2], the way certain letters are written (letter “t” and letter “y” in [3]) as well as other patterns, such as, for example, the trajectory of the writing [4]. 1 PhD student, Department of Telecommunications, University POLITEHNICA Bucharest, Romania, e-mail: mike.gavrilescu@gmail.com