Research on Personality Prediction Technology Based on Self-Introduction Video

Subjects: Psychology >> Applied Psychology Subjects: Computer Science >> Computer Application Technology submitted time 2020-03-08

温业业 陈德元 李保滨 汪晓阳 刘晓倩 朱廷劭

Abstract： Personality affects the individual's work and life style, and has important guiding significance for the individual's psychological counseling and career development. Traditional methods use personality scales to evaluate personality scores, which include problems such as individual refusal to answer and blind answering. In recent years, with the development of machine learning, new ideas have been provided for personality recognition. This article uses participants' self-introduction videos and Big Five personality scale scores to obtain different prediction models for different personality dimensions through key point extraction, feature dimension reduction, modeling, and iterative tuning. This article uses participants' self-introduction videos and Big Five personality scale scores to obtain different prediction models for different personality dimensions through key point extraction, feature dimension reduction, modeling, and iterative tuning. The test results show that the personality prediction model based on the self-introduction video is close to or achieves medium correlation in all dimensions, and can provide non-intrusive automatic personality recognition,, which provides new ideas for personality measurement.

Peer Review Status:Awaiting Review

 Hits 22864  Downloads 2830  Comment