The aim of this research work is to assess the likelihood of dairy farmers to accept predefined policy scenarios that implies different level of CO2 taxation on GHG emissions produced by the livestock sector. It uses an agent-based model (ABM) and it follows the positive mathematical programming (PMP) approach. ABMs allow to evaluate agricultural policies and farmers’ level of acceptance simulating interaction between farmers, taking territorial specificity and farm heterogeneity into account. The PMP methodology enables to add social and cultural perspective to the economical drivers. The Least Square method, applied to the PMP methodology, allows to overcome shortage in data availability. The model is calibrated on FADN data for the Emilia Romagna region (Italy), year 2020. Results show that farmers take decisions based on economic profitability but also on social and cultural background. Farmers opt for more efficient agricultural management practices if economically convenient, however the possibility to exchange production factors can contribute to the optimisation of their utility function.