Psychological research in the digital age

Kunz, Fiona (2023): Psychological research in the digital age: leveraging smartphones to predict psychological constructs in daily life. Dissertation, LMU München: Fakultät für Psychologie und Pädagogik

Abstract

The smartphone has become an important personal companion in our daily lives. Each time we use the device, we generate data that provides information about ourselves. This data, in turn, is valuable to science because it objectively reflects our everyday behavior and experiences. In this way, smartphones enable research that is closer to everyday life than traditional laboratory experiments and questionnaire-based methods. While data collected with smartphones are increasingly being used in the field of personality psychology, new digital technologies can also be leveraged to collect and analyze large-scale unobtrusively sensed data in other areas of psychological research. This dissertation, therefore, explores the insights that smartphone sensing reveals for psychological research using two examples, situation and affect research, making a twofold research contribution. First, in two empirical studies, different data types of smartphone-sensed data, such as GPS or phone data, were combined with experience-sampled self-report, and classical questionnaire data to gain valuable insights into individual behavior, thinking, and feeling in everyday life. Second, predictive modeling techniques were applied to analyze the large, high-dimensional data sets collected by smartphones. To gain a deeper understanding of the smartphone data, interpretable variables were extracted from the raw sensing data, and the predictive performance of various machine learning algorithms was compared. In summary, the empirical findings suggest that smartphone data can effectively capture certain situational and behavioral indicators of psychological phenomena in everyday life. However, in certain research areas such as affect research, smartphone data should only complement, but not completely replace, traditional questionnaire-based data as well as other data sources such as neurophysiological indicators. The dissertation also concludes that the use of smartphone sensor data introduces new difficulties and challenges for psychological research and that traditional methods and perspectives are reaching their limits. The complexity of data collection, processing, and analysis requires established guidelines for study design, interdisciplinary collaboration, and theory-driven research that integrates explanatory and predictive approaches. Accordingly, further research is needed on how machine learning models and other big data methods in psychology can be reconciled with traditional theoretical approaches. Only in this way can we move closer to the ultimate goal of psychology to better understand, explain, and predict human behavior and experiences and their interplay with everyday situations.

• Dokumententyp: Dissertationen (Dissertation, LMU München)
• Themengebiete: 100 Philosophie und Psychologie ; 100 Philosophie und Psychologie > 150 Psychologie
• Fakultäten: Fakultät für Psychologie und Pädagogik
• Sprache der Hochschulschrift: Englisch
• Datum der mündlichen Prüfung: 16. November 2023
• 1. Bericht­erstatter:in: Bühner, Markus