The Impact of Affective Verbal Content on Predicting Personality Impressions in YouTube Videos

Human nature as always implies massive challenges for predictive modeling that are yet to be fully explored. In this paper, we report on an experiment that examines the predictive effect of the gender and the affective content of video transcripts on predicting personality impressions of the person being judged. While gender had positive impact on the predictability across all personality traits, the effects of the emotional features varied across traits. Coarse-grain emotional categories resulted in performance gains for Agreeableness and Neuroticism, while the inclusion of fine-grain emotional features had more positive effect on predicting Extroversion and Openness to Experiences. The initial results are encouraging and comparable to related research.