Personality and individual differences: the potential of using preferences for visual stimuli to predict the Big Five traits

Although personality dimensions figure prominently in what people prefer or like about a display, little is known about precisely how personality dimensions can be predicted through our visual preferences. We investigated the feasibility for predicting continuous dimensions of personality traits (Big Five dimensions) from preferences captured by users' eye movements while scanning the preferred regions in a visual presentation. The eye-movement behavior of 96 participants was examined to identify their preferences in five visual design presentations. A multi-target learning method was used to build the prediction model of continuous dimensions of personality based on fixation and saccadic eye parameters. The results showed that participants' preferences for certain visual elements tended to explain their personality profile. Our findings offer new insights for personality assessment, human-computer interaction, personalization, and rational choice theories. It also addresses new trends related to the regulation of eye movements toward regions of interest based on the proportion of personality dimensions.