From Digital Data to Psychological Insights: Making Sense of Mobile-Sensing Data Through Integrative Preprocessing Pipelines

Psychological research has long centered around questionnaire assessments, butnow digital devices, especially smartphones, enable the collection of real-worldbehavioral data through mobile sensing. While this data collection method offersunique opportunities, it also introduces new methodological challenges, asmobile-sensing data are highly complex and high in dimensionality (i.e., time-stampedevents with millisecond resolution), requiring advanced preprocessing to derivepsychologically meaningful variables. This article highlights these challenges byreviewing the current state of data preprocessing based on app usage logs fromsmartphones. Afterwards, it presents three preprocessing cases that vary in complexityacross the dimensions of data enrichment—which involves adding context to raw databy integrating information from external and internal sources (including EcologicalMomentary Assessments)—and data aggregation—which entails summarizing data indifferent ways, from basic descriptive statistics to sophisticated machine learningmodels. For each case, potential pitfalls are identified, and extensions are discussed torefine our preprocessing pipelines and accommodate different data types and researchquestions. By outlining these preprocessing strategies, this manuscript demonstratesthe rich potential of mobile-sensing data for extracting nuanced behavioral variablesbeyond simple person-level summaries, and aims to inspire the development of moreadvanced research questions based on sensing data.