Skeleton-based Personality Recognition using Laban Movement Analysis.

Personality is expressed through multiple behavioral elements, including body movement. Using a feature transformation based on Laban Movement Analysis, we present a model for estimating individuals’ Big Five personality traits. Our approach achieves higher performance than other methods without exposing image-level information to the network, which otherwise can leave the system susceptible to bias and result in ethical issues. With the ever-increasing role of computers in our daily lives, human-computer interaction and human understanding have become significant. Our system enables better human understanding for intelligent agents and personal assistants through personality estimation. We utilize Graph Convolutional Networks, commonly used for action recognition for this task.