Uses of Computational Demography and digital footprint data for human mobility and migration studies

Patterns of Internal Migration and Interurban Mobility: Measurement, Description, and Prediction through Digital Footprints within the last two decades

The digital footprint represents the trail of digital activities and information generated by humans when interacting with digital platforms and services (Rowe et al., 2023). It enables us to estimate the influence of technology on migration patterns, develop predictive models, promote migration governance, facilitate data exchange between countries, and strengthen global governance institutions. Through “data science and artificial intelligence for social good,” the sustainable development goals provide a framework for government responses to social demands (Tomašev et al., 2020).

In this context, the goal of this project is to analyse internal migration and interurban mobility within the last two decades, using digital footprints alongside census data. To achieve this, we will develop a valid, reliable descriptive, analytical, and predictive model for internal migration and interurban mobility using computational languages, such as Python and R. Datasets from Facebook users (with anonymised past and current location data) will be used, complemented by public interaction data from X (formerly Twitter), accessed through Python (Tweepy) and R (R-Tweet). Due to issues of “representativeness” and “age bias” in digital footprint data, the last two national censuses will be consulted for validation.