Man-Machine Interaction Improvement by Means of Automatic Human Personality Identification
Autorzy/Authors: Ryszard Tadeusiewicz, Adrian Horzyk
Wydawnictwo/Publisher: Springer-Verlag, LNCS 8104, 2013, pp. 10
Abstract:
We most frequently concentrate on the semantic aspects of communication during planning and forming of man-machine interactions. For example striving to more acceptable (for users) forms of communication with numerous computer applications we put big effort for increasing of machine intelligence, developing more advances methods of automatic reasoning and enriching quantity and quality of knowledge built-in into computer resources. Meanwhile emotions and adequate reactions on needs play equally essential role as rational reasoning when judge intelligence of a partner. Intelligent behaviours and reactions usually deliberately affect the needs of a partner. Therefore a computer could be accepted as intelligent (or even liked) partner in cooperation with the man if it will consider human needs affecting emotions. Such needs must be first recognized. Such recognition must be performed during natural interactions between man and machine, because nobody likes to be tested or examined before can start a merit communication with a chosen computer application. Moreover nobody can honestly and objectively classify own personality, therefore we cannot obtain necessary information asking a person about his or her features of personality and its needs. This paper presents a new method of automatic human needs recognition. Personality and needs of the partner can be recognized listening or watching the following behaviours:
- verbal, i.e. a way of talking, frequently used vocabulary, phrases, inflection, construction of sentences etc.
- non-verbal (body language), i.e. facial and body expressions, a way of movement, dressing-up, driving cars, bicycles, environment, family etc.
During typical man-machine communication we can perform automatic passive classification of man personality by means of psycholinguistic analysis. Details how this personality can be discovered during natural language man-machine communication will be presented during the lecture.
Keywords:
personality model, typology of personality, personality identification, personality recognition, personality classification, man-machine interface, man-machine interaction.