Abstract
In this paper, we propose a Relational Knowledge Transfer (RKT) model to predict Chinese ancient emperors’ personalities. It make good use of relational history semantic knowledge including Chinese emperors’ self-claimed character “朕”, statistics knowledge about correlation coefficient, and psychological knowledge including personality scores having normal distribution, to produce the virtual training datasets. With the Domain-Adversarial Training of Neural Network’s learning ability, we transferred human knowledge to the machine well with little manual data annotation effort. Compared with original version of PAP-TL tool, latest version of RKT model achieved the state of art in terms of the prediction accuracy of the Big Five personality scores of ancient Chinese emperors, with RMSE on average decreased from 9.16 to 5.40 (by 41%). This RKT model can be further applied to predict the personalities of Chinese of a specific group or period in the more than 2000 years ancient history.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Mccrae, R.R., Jüri Allik, E.: The five factor model of personality accross cultures. In: Marsella, A.J. (ed.) International and Cultural Psychology Series, p. 336. Kluwer Academic/Plenum Publishers, New York (2002)
Heidi, S.: Wu Zetian's personality and important interpersonal relationships. Wuhan University (2014)
Xianjiao, C.: The Personality of Ming Shenzong. Hunan Normal University (2013)
Xing, F., et al.: Predicting Personality of Ancient People based on Transfer Learning. IFAC PapersOnLine 53(5), 470–475 (2020)
Palatucci, M.P.D., Hinton, G., Mitchell, T.M.: Zeroshot learning with semantic output codes. In: Proceedings of the 22nd International Conference on Neural Information Processing Systems, pp. 1410−1418 (2009)
Wang, D., et al.: Relational knowledge transfer for zero-shot learning. In: Thirtieth AAAI Conference on Artificial Intelligence (2016)
Romera-Paredes, B., Ox, E., Torr, P.H.: An embarrassingly simple approach to zero-shot learning. ICML, pp. 2152–2161 (2015)
Zhang, L., Gao, X.: Transfer adaptation learning: A decade survey. arXiv preprint arXiv:1903.04687 (2019)
Ganin, Y., et al.: Domain-adversarial training of neural networks. J. Mach. Learn. Res. 17(17), 1–35 (2016)
Miaorong, F., et al.: Classical Chinese LIWC: A Brief Introduction and Pilot Analysis (2019)
Pennebaker, J.W.: Linguistic styles: language use as an individual difference. J. Pers. Soc. Psychol. 77(6), 1296–1312 (1999)
Tausczik, Y.R., Pennebaker, J.W.: The psychological meaning of words: LIWC and computerized text analysis methods. J. Lang. Soc. Psychol. 29(1), 24–54 (2010)
Mairesse, F.M.A.W., Mehl, M.R., Moore, R.K.: Using linguistic cues for the automatic recognition of personality in conversation and text. Artif. Intell. Res. 30, 457–500 (2010)
Gao, R., et al.: Developing Simplified Chinese Psychological Linguistic Analysis Dictionary for Microblog. Springer International Publishing, Cham (2013)
Rothmann, S., Coetzer, E.P.: The big five personality dimensions and job performance. SA J. Ind. Psychol. 29(1), 68–74 (2003)
Xue, D., et al.: Personality recognition on social media with label distribution learning. IEEE Access 5, 13478–13488 (2017)
Rosenblatt, M.: A central limit theorem and a strong mixing condition. Proc. Natl. Acad. Sci. U.S.A. 42(1), 43 (1956)
Hendriks, A.A.J., Hofstee, W.K.B., Raad, B.D.: The Five-Factor Personality Inventory (FFPI). Personality and Individual Differences 27(2), 307–325 (1999)
Carciofo, R., et al.: Psychometric evaluation of chinese-language 44-Item and 10-Item big five personality inventories, including correlations with chronotype, mindfulness and mind wandering. PLoS ONE 11(2), e0149963 (2016)
Roy, R.: Comparison of different techniques to generate Normal random variables. Journal of East Central Europe 545, 5–6 (2002)
Zhang, X., et al.: Deep Transfer Network: Unsupervised Domain Adaptation. arXiv preprint arXiv:1503.00591 (2015)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Xiao, H., Xing, F., Fan, M., Li, H., Zhu, T. (2022). Predicting Personalities of Ancient Chinese Emperors Based on Relational Knowledge Transfer Model. In: Zu, Q., Tang, Y., Mladenovic, V., Naseer, A., Wan, J. (eds) Human Centered Computing. HCC 2021. Lecture Notes in Computer Science, vol 13795. Springer, Cham. https://doi.org/10.1007/978-3-031-23741-6_7
Download citation
DOI: https://doi.org/10.1007/978-3-031-23741-6_7
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-23740-9
Online ISBN: 978-3-031-23741-6
eBook Packages: Computer ScienceComputer Science (R0)