Where do bosons actually belong?

We explore a variety of reasons for considering su(1, 1) instead of the customary h(1) as the natural unifying frame for characterizing boson systems. Resorting to the Lie-IIopf structure of these algebras, that shows how the Bose-Einstein statistics for identical bosons is correctly given in the su(1, 1) framework, we prove that quantization ofMaxwell's equations leads to su(1, 1), relativistic covariance being naturally recognized as an internal symmetry of this dynamical algebra. Moreover su(1, 1) rather than h(1) coordinates are associated to circularly polarized electromagnetic waves. As for interacting bosons, the su(1, 1) formulation of the Jaynes-Cummings model is discussed, showing its advantages over h(1).