This talk focuses on dynamic inference of hidden, time-varying, and sparse social networks that facilitate the diffusion of information (e.g., viral news, or spread of consumer habits). The key novelty in this work is recognizing that the dynamics of hidden networks are sometimes driven by switching behavior between discrete (and finite) states. The advocated model tacitly accounts for switching dynamics, and a novel efficient tracking algorithm that leverages proximal gradient methods is developed. Finally, preliminary test results on simulated data and real-world information cascades are presented.