Smartphones enjoy high adoption rates around the globe. Rarely more than an arm’s length away, these sensor-rich devices can easily be repurposed to collect rich and extensive records of their users’ behaviors (e.g., location, communication, media consumption), posing serious threats to individual privacy. Here we examine the extent to which individuals’ Big Five personality dimensions can be predicted on the basis of six different classes of behavioral information collected via sensor and log data harvested from smartphones. Taking a machine-learning approach, we predict personality at broad domain (rmedian= 0.37) and narrow facet levels (rmedian= 0.40) based on behavioral data collected from 624 volunteers over 30 consecutive days (25,347,089 logging events). Our cross-validated results reveal that specific patterns in behaviors in the domains of 1) communication and social behavior, 2) music consumption, 3) app usage, 4) mobility, 5) overall phone activity, and 6) day- and night-time activity are distinctively predictive of the Big Five personality traits. The accuracy of these predictions is similar to that found for predictions based on digital footprints from social media platforms and demonstrates the possibility of obtaining information about individuals’ private traits from behavioral patterns passively collected from their smartphones. Overall, our results point to both the benefits (e.g., in research settings) and dangers (e.g., privacy implications, psychological targeting) presented by the widespread collection and modeling of behavioral data obtained from smartphones.

No abstract

For decades, day–night patterns in behaviour have been investigated by asking people about their sleep–wake timing, their diurnal activity patterns, and their sleep duration. We demonstrate that the increasing digitalization of lifestyle offers new possibilities for research to investigate day–night patterns and related traits with the help of behavioural data. Using smartphone sensing, we collected in vivo data from 597 participants across several weeks and extracted behavioural day–night pattern indicators. Using this data, we explored three popular research topics. First, we focused on individual differences in day–night patterns by investigating whether ‘morning larks’ and ‘night owls’ manifest in smartphone‐sensed behavioural indicators. Second, we examined whether personality traits are related to day–night patterns. Finally, exploring social jetlag, we investigated whether traits and work weekly day–night behaviours influence day–night patterns on weekends. Our findings highlight that behavioural data play an essential role in understanding daily routines and their relations to personality traits. We discuss how psychological research can integrate new behavioural approaches to study personality.

Abstract. The increasing usage of new technologies implies changes for personality research. First, human behavior becomes measurable by digital data, and second, digital manifestations to some extent replace conventional behavior in the analog world. This offers the opportunity to investigate personality traits by means of digital footprints. In this context, the investigation of the personality trait sensation seeking attracted our attention as objective behavioral correlates have been missing so far. By collecting behavioral markers (e.g., communication or app usage) via Android smartphones, we examined whether self-reported sensation seeking scores can be reliably predicted. Overall, 260 subjects participated in our 30-day real-life data logging study. Using a machine learning approach, we evaluated cross-validated model fit based on how accurate sensation seeking scores can be predicted in unseen samples. Our findings highlight the potential of mobile sensing techniques in personality research and show exemplarily how prediction approaches can help to foster an increased understanding of human behavior.

We implemented several multilabel classification algorithms in the machine learning package mlr. The implemented methods are binary relevance, classifier chains, nested stacking, dependent binary relevance and stacking, which can be used with any base learner that is accessible in mlr. Moreover, there is access to the multilabel classification versions of randomForestSRC and rFerns. All these methods can be easily compared by different implemented multilabel performance measures and resampling methods in the standardized mlr framework. In a benchmark experiment with several multilabel datasets, the performance of the different methods is evaluated.

Theories derived from lab-based research emphasize the importance of mentalizing for social interaction and propose a link between mentalizing, autistic traits, and social behavior. We took social cognitive research outside the lab to test these assumptions in everyday life. Via smartphone-based experience sampling and logging of smartphone usage behavior we quantified mentalizing and social interaction in our participants' natural environment. Both measures were compared with autistic traits, controlling for Big Five personality dimensions, social anxiety, and verbal intelligence. Mentalizing occurred less frequently than reasoning about actions and participants preferred to mentalize when alone. Autistic traits were negatively correlated with communication via smartphone. Yet, they were not associated with social media usage, a more indirect way of getting in touch with others. We further found no relation between autistic traits and social network size. These findings critically inform recent theories on social cognition and behavior in individuals with and without autism.

Interpretable machine learning has become a very active area of research due to the rising popularity of machine learning algorithms and their inherently challenging interpretability. Most work in this area has been focused on the interpretation of single features in a model. However, for researchers and practitioners, it is often equally important to quantify the importance or visualize the effect of feature groups. To address this research gap, we provide a comprehensive overview of how existing model-agnostic techniques can be defined for feature groups to assess the grouped feature importance, focusing on permutation-based, refitting, and Shapley-based methods. We also introduce an importance-based sequential procedure that identifies a stable and well-performing combination of features in the grouped feature space. Furthermore, we introduce the combined features effect plot, which is a technique to visualize the effect of a group of features based on a sparse, interpretable linear combination of features. We used simulation studies and real data examples to analyze, compare, and discuss these methods.

No abstract