Personality Research and Assessment in the Era of Machine Learning

Abstract

The increasing availability of high-dimensional, fine-grained data about human behavior, gathered from mobile sensing studies and in the form of digital footprints, is poised to drastically alter the way personality psychologists perform research and undertake personality assessment. These new kinds and quantities of data raise important questions about how to analyze the data and interpret the results appropriately. Machine learning models are well-suited to these kinds of data, allowing researchers to model highly complex relationships and to evaluate the generalizability and robustness of their results using resampling methods. The correct usage of machine learning models requires specialized methodological training that considers issues specific to this type of modeling. Here, we first provide a brief overview of past studies using machine learning in personality psychology. Second, we illustrate the main challenges that researchers face when building, interpreting, and validating machine learning models. Third, we discuss the evaluation of personality scales, derived using machine learning methods. Fourth, we highlight some key issues that arise from the use of latent variables in the modeling process. We conclude with an outlook on the future role of machine learning models in personality research and assessment.

‘Personality in its Natural Habitat’ Revisited: A Pooled, Multi–sample Examination of the Relationships between the Big Five Personality Traits and Daily Behaviour and Language Use

“…The project is a rich culminating product of the traditional smaller‐scale, handmade personality studies of the early 2000s. At the same time, it can stand in comparison with the modern, technology‐enhanced, big(ger)‐data, mobile sensing personality studies and highlights their value and unique potentials (Harari et al, 2019; Montag & Elhai, 2019; Stachl et al, 2020). And, last but not least, as the need for replication is becoming clear and consensually accepted in the field (Zwaan, Etz, Lucas, & Donnellan, 2018), the project can also serve as a reminder to try to replicate not only easily reproduced research but also the more resource‐intensive and challenging‐to‐conduct studies (Sassenberg & Ditrich, 2019), so that psychology will over time accrue a solid knowledge base of replicated facts of the broadest possible range of its science.…”

Targeting Item–level Nuances Leads to Small but Robust Improvements in Personality Prediction from Digital Footprints

“…In contrast to the relative performance measures more common in machine learning research in psychology (e.g. Pearson and Spearman correlations), these absolute measures in effect capture how far off predictions are from actual values rather than capturing a general tendency of predictions to be higher or lower than observed values (Stachl, Pargent, et al, 2019). Interestingly, the absolute measures showed very little difference between models in the present case, suggesting that the nuance models tend to perform better than trait models when predicting rank associations but may not offer as competitive of an advantage in absolute value prediction.…”

How Are Personality States Associated with Smartphone Data?

“…A further advantage of XGBoost compared with neural networks is that it can handle missing values appropriately without the need for imputation. The second and third model are ridge regression (Hoerl & Kennard, 1970; James et al, 2013) and lasso regression (James et al, 2013; Tibshirani, 1996), which are two variations of regularized regression algorithms (Xing, Jordan, & Karp, 2001) and which have been widely used, including in personality research (Hall & Matz, 2020; Seeboth & Mõttus, 2018; Stachl et al, 2017; Stachl et al, 2019). Finally, we also explored ordinary least squares regression.…”

“…With mobile sensing methods, personality science is gaining new opportunities for studying people's behaviours in daily life (Harari et al, 2016; Stachl et al, 2020a). As an innovative approach for unobtrusive ambulatory behavioural assessments (Trull & Ebner‐Priemer, 2014), mobile sensing using everyday devices that many people carry around most of their day (e.g.…”

“…A number of articles have highlighted the potential of machine learning approaches for personality research (Bleidorn & Hopwood, 2018; Stachl et al, 2020a; Yarkoni & Westfall, 2017). They emphasized a number of strengths, including the ability to handle a large number of predictor variables even with relatively small data sets, and the potential to achieve high prediction performance (Yarkoni & Westfall, 2017).…”