I am a psychologist specializing in personality and human factors psychology, behavioral sensing methodology, and predictive modeling. This website provides a short summary of my research activities. My work can be categorized into two complementary themes that build on one another:
- First, I use consumer electronics to measure how individuals differ in their behavior with regard to demographic and psychological dispositions.
- Second, I investigate how people use technology and how human-computer interaction can be improved by considering the user-characteristics.
Understanding Individual Differences in Behavior Using Consumer Electronics
In the last century, it has been almost impossible to collect ecologically valid data about people's daily behavior in an objective way and at a large scale. However, the pervasiveness and the technical capabilities of modern consumer electronics (e.g., smartphones, cars) in terms of sensors, computational abilities, and connectivity now make it possible to do so. In my research, I use smartphone applications to gather data about a wide range of behavior in the wild (e.g., sociability, media use, mobility).
For the last six years, I was head of the PhoneStudy research project at the Ludwig-Maximilians-Universität München. The PhoneStudy project uses a mobile sensing Android application to automatically collect longitudinal data about behavioral and situational characteristics (e.g., communication, app-use, location and physical activity, media use, speech parameters, language use). I used these data to investigate how the usage of different types of smartphone applications is related to personality traits, demographics, and cognitive abilities (Stachl et al., 2017). For example, my research showed that extraverted people tended to make more but shorter calls, conscientious people played games less often on their phones, and more agreeable people used public transportation apps more frequently. In a series of follow up studies in this line of research, me and others mapped out the relationships between personality traits and sociability behaviors in the wild (Harari et al., 2019), related behavioral data to the autism spectrum (Schuwerk et al., 2019) and investigated the behavioral factors of sensation seeking as a personality trait (Schoedel et al., 2018). Aside from sensing data, I was also assisting work on the detection of simulated and dissimulated symptoms of depression by machine learning from questionnaire data (Goerigk et al., 2018).
In my latest project, me and coaleges show that the breadth of behavioral and situational data that can be collected with smartphones can reveal people's personality traits (Stachl et al., under revision). I used machine learning models to predict self-reported personality trait scores from thousands of behavioral variables. In addition, I used interpretable machine learning techniques, which allowed me to identify patterns in traceable behaviors that were distinctively revealing of specific personality traits. For example, we found that on average, higher scores in conscientiousness were predicted for people with a higher regularity in their daily behaviors. Our findings also highlight the privacy problems raised by everyday smartphone usage and provide new evidence for behavioral manifestations of personality traits.
For my work on mobile sensing in personality psychology, I recently received the Award for Digital Assessment from the German Society for Personality Psychology and Psychological Assessment.
Another positive outcome of my work on smartphone sensing was to collaborate with others on the development of new research methods. During the last six years, I helped to publish on the development of new machine learning methods (Au et al., 2018, Probst et al., 2017), with the generation of new ideas for experience sampling methods (Buschek et al., 2018) and in the conceptualization of an R-package for easy aggregation of grouped sensing data (Au et al. , 2019).
See research activities in relation to the PhoneStudy project on the Open Science Framwork: https://osf.io/ut42y/
Improving Human Computer Interaction through Personalization
In addition to work on mobile sensing in academic settings, I could closely work with engineers, data scientists and computer scientists on in-car functionalities in the German car industry sector. Initially, I focused on the optimization of digital systems and interfaces to improve life for all users (e.g., Stachl & Bühner, 2012, Schoedel et al., 2018). However, the design of digital systems and their user interfaces can also be optimized to user-inherent characteristics, such as personality traits, demographics (Scheider et al., 2017, Schoedel et al., 2018, Stachl et. al 2015), and user-states (Völkel et al., 2018).
In the last three years, I was leading my own team of researchers (Ramona Schödel, Sarah Theres Völkel, Quay Au) in a fully funded research project (“User-Centered Machine Learning”) together with the Audi car company. The vision of this project was to rethink adaptive user interfaces by considering user-characteristics in the design process (e.g., demographics, personality traits, mental states) and to improve the interaction between the user and the system through automated personalization, based on these characteristics. Most recently, we finished work on a personality trait theory for artificial, conversational agents (Völkel et al., 2020)
I embrace the values of openness and transparency in science. I believe that such research practices increase the informational value and impact of our research, as the data can be reanalyzed and synthesized in future studies. Furthermore, they increase the credibility of the results, as an independent verification and replication is possible.
For this reason, I signed the Commitment to Research Transparency.
My research interests in social media language:
#behavior, #mobilesensing, #machinelearning, #personality, #personalization, #humanfactors