In this paper, we introduce and study mathematical programming formulations for the Least Cost Directed Perfect Awareness Problem (LDPAP), an NP-hard optimization problem that arises in the context of influence marketing. In the LDPAP, we seek to identify influential members of a given social network that can disseminate a piece of information and trigger its propagation throughout the network. The objective is to minimize the cost of recruiting the initial spreaders while ensuring that the information reaches everyone. This problem has been previously modeled as two different integer programming formulations that were tested on a collection of 300 small synthetic instances. In this work, we propose two new integer programming models and three constraint programming formulations for the LDPAP. We also present preprocessing techniques capable of significantly reducing the sizes of these models. To investigate and compare the efficiency and effectiveness of our approaches, we perform a series of experiments using the existing small instances and a new publicly available benchmark of 14 large instances. Our findings yield new optimal solutions to 185 small instances that were previously unsolved, tripling the total number of instances with known optima. Regarding both small and large instances, our contributions include a comprehensive analysis of the experimental results and an evaluation of the performance of each formulation in distinct scenarios, further advancing our understanding of the LDPAP toward the design of exact approaches for the problem.