The 2008 presidential election was a "perfect storm" for pollsters. A significant portion of the population had exchanged their landlines for cellphones, which made them harder to survey. Additionally, a potential Bradley effect -- in which white voters misrepresent their intentions of voting for or against a black candidate -- skewed predictions, and aggressive voter registration and mobilization campaigns by Barack Obama combined to challenge conventional understandings about how to measure and report public preferences. In the wake of these significant changes, "Political Polling in the Digital Age," edited by Kirby Goidel, offers timely and insightful interpretations of the impact these changes will make on polling.
US-centric, and outdated in light of political polling's recent high-profile failures, this book still provides a good entry-point into understanding the phenomenon, the theory behind it, how to consider and interact with polling and polling data, as well as its challenges and limitations.
Not a how-to guide, but a conference proceedings. Has a bit on doing modern polling, but not much specific direction. Well-written essays overall, with perspectives on polling history.