A fundamental open question that has been studied by sociologists since the 70s and recently started being addressed by the computer-science community is the understanding of the role that influence and selection play in shaping the evolution of socio-cultural systems. Quantifying these forces in real settings is still a big challenge, especially in the large-scale case in which the entire social network between the users may not be known, and only longitudinal data in terms of masses of cultural groups (e.g., political affiliation, product adoption, market share, cultural tastes) may be available. We propose an influence and selection model encompassing an explicit characterization of the feature space for the different cultural groups in the form of a natural equation-based macroscopic model, following the approach of Kempe et al. [EC 2013]. Our main goal is to estimate edge influence strengths and selection parameters from an observed time series. To do an experimental evaluation on real data, we perform learning on real datasets from Last. FM and Wikipedia.