This paper presents an analysis and a classification of adaptive systems with respect to the kind of semantic technology they exploit to accomplish or improve specific adaptation and user modeling tasks. This classification is based on a distinction between strong semantic techniques and weak semantic techniques. The former techniques are based on the Semantic Web, while the latter regard technologies that, in different ways, annotate resources, enriching their meaning. This second category includes, in particular, Web 2.0 social annotations and mixed approaches between social annotations and Semantic Web techniques. While the impact of the Semantic Web on adaptive systems has been discussed in several survey papers, the potential of weak semantic technologies has received less attention. The original contribution of this study is to fill this gap by providing an overall analysis of the use of all forms of knowledge annotation to implement and carry out task and sub-tasks of user modelling and user-adapted systems.