View article

The real world application scenarios for automatic prediction of apparent personality traits are vast and fall within a wide range of domains such as entertainment, health, human computer interaction, recruitment and security. These predictions can be critical for individuals in many scenarios (eg, hiring an applicant). However, these predictions in and of themselves might be deemed to be untrustworthy without further supportive evidence in such scenarios. Through a series of experiments on a recently released benchmark dataset for automatic apparent personality trait prediction, this paper characterizes the audio and visual information that is used by a state-of-the-art model while making its predictions so as to provide such supportive evidence by explaining these predictions. Additionally, it describes a new web application, which gives feedback on apparent personality traits of its users by combining model predictions with their explanations.