“…Using a simple decision-making battery programmed in accordance with the trade-off framework, traits as diverse as political affiliation, communication skills, gender identity, spirituality, and social preferences-traits that serve as real-world manifestations of personality differences across individuals-were all predicted at levels statistically significant at p-values less than .00001. To the knowledge of the author, the machine-learning-generated linear regressions between the features of the FFM trade-off framework and self-reported attitudes and beliefs are state-of-the-art; despite performing a fairly exhaustive literature review, no existing research could be found that claimed to uncover correlations between personality and political, social, professional, academic, and personal attitudes that approach the magnitude of those described in the linear regression experiments in Table 4 (e.g., Rosenfeld, 2018;Forrester and Tashchian, 2010;Chirumbolo and Leone, 2010;Lowicki, 2019;Erceg et al, 2018;Birkeland and Buch, 2015;Sutin et al, 2012;Moss and O'Connor, 2020). By simply inputting a numerical representation of an individual's hierarchy of motivations into the machine learning models generated by this research, the correct half of each of the attitudinal spectra upon which the individual self-identified (e.g., more liberal, or more conservative?)…”