Human psychology plays an important role in organizational performance. However, understanding our employees is a difficult task due to issues such as psychological complexities, unpredictable dynamics, and the lack of data. Leveraging evidence-based psychology knowledge, this paper proposes a hybrid machine learning plus ontology-based reasoning system for detecting human psychological artifacts at scale. This unique architecture provides a balance between system's processing speed and explain-ability. System outputs can be further consumed by graph science and/or model management system for optimizing business processes, understanding team dynamics, predicting insider threats, managing talents, and beyond.