Machine learning at the learner’s hand: a support to theory formation in collaborative discovery learning environments

In the last decade the design of collaborative discovery learning environments (CDLE’s) has received increasing attention. In this paper, we are concerned with the design of CDLE’s in which theory formation arises as a synergetic combination of both inductive and hypothetical-deductive approaches. The “moving engine” allowing a theory to evolve is the notion of contradiction: learning is supposed to occur as a side effect of contradiction detection and overcoming during theory formation by peers. By playing different roles, peers are assisted by an Artificial Agent capable of both inducing and deducing. The dynamics within the environment is illustrated through a scenario.