Gender Identification of VR Users by Machine Learning Tracking Data

Gender identification of virtual reality (VR) users by machine learning tracking data could afford personalized experiences, including mitigation of expected human factors or psychology issues. While much research has recently been conducted to identify individual users given their VR tracking data, little research has investigated gender identification. Furthermore, nearly all prior studies have only considered positions and rotations of all the devices. We present a systematic investigation of different combinations and spatial representations of VR tracked devices for predicting a user's gender. Our results indicate head rotations are integral to gender identification while head positions are surprisingly not as important.