The science behind technology
HRMNY AI is built on decades of research in psychology, cognitive sciences and artificial intelligence. Get the tools and data to finally start making data-driven decisions in all areas of the business.
“Any sufficiently advanced technology is indistinguishable from magic.”
Arthur C. Clarke
How it all began
Analytical psychology and personality traits
Analytical psychology or Jungian analysis distinguishes several psychological traits or ways people characteristically perceive, and then act upon, information. Carl Gustav Jung identified core psychological processes as well as functions of the psyche through which people are experiencing the world (Jung, Storr).
These "preferences" are inborn and not socially constructed through interaction with our family, social circle, culture, or other external influences (Jung, Storr). Even so, the individual is impacted by the quality and strength of the development in their preferences. As both nature and nurture greatly influence personality, a favorable environment supports and facilitates inborn preference development. In contrast, a hindering environment will impede or delay the natural development of these preferences or traits (Geyer).
Methods of modelling personality
Researchers use various schemes for personality modelling by setting a number of classification dimensions. The most popular are the Myers-Briggs Type Indicator, Eysenck’s PEN model, DISC, the Big-Five personality traits, and Socionics. Personality modelling methodologies explore the underlying dynamics of human psyche, such as dominant drives, motives, needs for achievement, power, or intimacy — traits of a person's character that are stable across situations.
Self-assessment for mapping personality traits
For the purpose of mapping traits various self-assessment tests like TAT, MBTI, DISC, and Big Five personality traits test are used. However, surveys and self-assessment — interventions that over time have been proven to become an origin of distortions and manipulations. Respondents often provide results of low reliability and validity, giving inaccurate information, misrepresenting or enhancing their image (Strube, Lott et al). Another flaw of this method is that the procedure is time-consuming and often not standardized.
Links between facial features and personality traits
Compared to self-assessments, observational methods of determining personality traits from the way a person looks like, talks or writes and represents themselves is a user-friendly solution. The approach which involves the analysis of facial features (like shape of nose, eyebrows) for personality prediction is proven to be accurate, valid and reliable (Kamenskaya and Kukharev).
Recently, the automatic prediction of personality traits has received a lot of attention. A growing number of studies link facial images to personality. Michal Kosinski, the Stanford University professor, examines findings about links between image and personal traits in several studies, and confirms that AI is more accurate than humans when it comes to determining those traits. For example, it was possible to expose political orientation from facial images (Kosinski) as well as sexual orientation (Wang and Kosinski) using deep neural networks and facial recognition.
An Unbiased AI solution
The flaws of the surveys and self-assessment methods as well as the advantages and convenience of the observational ones led us to investigate only observational methods for mapping personality in our research, merging them later with an automated solution.
As in the case of most visual deep learning tasks, convolutional neural networks (CNNs) achieve the best results in the field of personality detection from real-life photographs containing cues about personality. For the last several years we trained our CNN models on large, labeled datasets, allowing us to predict multidimensional personality profiles from static facial images, short videos, and audio materials. An accurate, fast, and unbiased AI solution now demonstrates a highly reliable method of detecting and assessing cognitive traits. This is HRMNY AI.
-
1. Borkenau P., Brecke S., Möttig C., Paelecke M. (2009). Extraversion is accurately perceived after a 50-ms exposure to a face; J. Res. Pers. 43, 703–706
2. Briggs Myers I.; Kirby L.K.; Myers K.D. (2015). Introduction to Myers-Briggs type: a guide to understanding your results on the MBTI assessment. Palo Alto, Calif. : Consulting Psychologists Press
3. Cristani M., Vinciarelli A., Segalin C., Perina A. (2013). Unveiling the multimedia unconscious: implicit cognitive processes and multimedia content analysis; Proceedings of the 21st ACM international conference on Multimedia, pp. 213–222. ACMGeyer,
4. Jung, C. G., and Antony Storr. (1983). The Essential Jung. Princeton, NJ: Princeton University Press.
5. Kamenskaya E., Kukharev G. (2008). Recognition of psychological characteristics from face; Metody Informatyki Stosowanej 1(1), 59–73
6. Kosinski, M. (2021). Facial recognition technology can expose political orientation from naturalistic facial images. Sci Rep 11, 100. https://doi.org/10.1038/s41598-020-79310-1
7. Kramer R. S. S., King J. E., Ward R. (2011). Identifying personality from the static, non expressive face in humans and chimpanzees: Evidence of a shared system for signaling personality; Evol. Hum. Behav. https://doi.org/10.1016/j.evolhumbehav.2010.10.005
8. Kulkarni, V., Kern, M.L., Stillwell, D., Kosinski, M., Matz, S., Ungar, L., Skiena, S., & Schwartz, H.A. (2018). Latent Human Traits in the Language of Social Media: An Open-Vocabulary Approach. PLOS ONE.
9. Little A. C., Perrett D. I. (2007). Using composite images to assess accuracy in personality attribution to faces; Br. J. Psychol. 98, 111–126
10. Naumann L. P., Vazire S., Rentfrow P. J., Gosling S. D. (2009). Personality judgments based on physical appearance; Personal. Soc. Psychol. Bull. 35, 1661–1671
11. Penton-Voak I. S., Pound N., Little A. C., Perrett D. I. (2006). Personality judgments from natural and composite facial images: more evidence for a “kernel of truth” in social perception; Soc. Cogn. 24, 607–640
12. Pervin L.A., John O.P. (1999). Handbook of personality: Theory and research, Elsevier
13. Peter. (2012). Extraversion – Introversion: what C.G. Jung meant and how contemporaries responded. AusAPT National Conference
14. Segalin, C., Celli, F., Polonio, L., Kosinski, M., Stillwell, D., Sebe, N., … Lepri, B. (2017). What your Facebook profile picture reveals about your personality. Proceedings of the 2017 ACM on Multimedia Conference.
15. Shevlin M., Walker S., Davies M. N. O., Banyard P., Lewis C. A. (2003). Can you judge a book by its cover? Evidence of self-stranger agreement on personality at zero acquaintance; Pers. Individ. Dif. https://doi.org/10.1016/S0191-8869(02)00356-2
16. Strube MJ, Lott CL, Lê-Xuân-Hy GM, Oxenberg J, Deichmann AK. (1986). Self-evaluation of abilities: accurate self-assessment versus biased self-enhancement. J Pers Soc Psychol. 1986 Jul;51(1):16-25. doi: 10.1037/0022-3514.51.1.16. PMID: 3735065.
17. Walker M., Vetter T. (2016). Changing the personality of a face: Perceived big two and big five personality factors modeled in real photographs; J. Pers. Soc. Psychol. 110, 609–624
18. Wang & Kosinski (2018) Deep neural networks are more accurate than humans at detecting sexual orientation from facial images. Journal of Personality and Social Psychology (JPSP)