Big Data is increasingly recognized for its substantial potential to enhance research on human behavior. Data from diverse sources, such as social media platforms, telecommunications companies, and mapping services like OpenStreetMap (OSM), provide a wealth of information. However, merely having this data is insufficient to fully grasp individuals’ socio-economic and personal contexts. While Big Data is effective for in-depth studies of specific aspects of human behavior, it often falls short of capturing the overall complexity of daily life.

For example, social media data facilitates sophisticated analyses of interactions within a platform but doesn’t adequately reflect the intricacies of real-world activities. Conversely, traditional social science methods—such as questionnaires, interviews, and participant observation—capture the nuances of daily routines and individual perspectives but have a different, more limited scale compared to Big Data.

In this context, the DataScientia (DS) initiative provides tools for gathering real-time behavioral data, combining insights from both individual interactions and sensor streams from personal devices, particularly smartphones. This approach is beneficial for researchers across various fields, from social sciences to computer science. The impact of this data is further amplified by integrating it with other secondary data, such as merging GPS data from smartphones with location descriptions and Points of Interest obtained from OSM.

However, collecting this type of data presents several challenges, including technological issues and privacy concerns, particularly regarding GDPR compliance. Researchers must also navigate potential errors due to participant interactions, such as response bias and participant burden, as well as prepare the data for distribution, addressing issues like data loss and lack of anonymization.

To help address these challenges, DS is equipped with several essential tools: