Digital twins in human understanding: a deep learning-based method to recognize personality traits

ABSTRACT

Digital twin models are computerized clones of physical assets or systems and have attracted much attention from academia and industries. Digital twin applications focus on smart manufacturing systems. Meanwhile, manufacturing products are driven increasingly by the needs of customers. Industrial production modes have evolved from mass production to personalized production. Understanding customers and meeting their personalized needs have become important issues in smart manufacturing. Social networks provide platforms for online customers to engage in different behaviors. In addition, personality recognition is a crucial issue for understanding people. In this study, a new technique is proposed to formalize personality as digital twin models by observing users’ posting content and liking behavior. A multitask learning deep neural network model is used to predict users’ personality through two types of data representation. Experimental results show that combining the two types of data can improve personality prediction accuracy.

KEYWORDS:

• Digital twin
• personality recognition
• deep neural network
• multitasking learning
• big five personality

Disclosure statement

No potential conflict of interest was reported by the authors.

Notes

1. https://keras.io.

2. http://mypersonality.org.

Additional information

Funding

This work is supported by the National Natural Science Foundation of China (71872060, 91846201, 71490725, 71722010, 91546114, and 91746302), 2019 Guangdong Special Support Talent Program – Innovation and Entrepreneurship Leading Team (China) (2019BT02S593) and the Fundamental Research Funds for the Central Universities of China (JZ2020HGPA0113), partially Sponsored by Zhejiang Lab (No. 2019KE0AB04).