On the Prospects of Intelligent Collaborative E-learning Systems Miikka Miettinen a,1 Jaakko Kurhila b and Henry Tirri c a Helsinki Institute for Information Technology, Finland b Department of Computer Science, University of Helsinki, Finland c Nokia Research Center, Nokia Group, Finland Abstract. Collaborative learning is question-driven and open-ended by nature. Many of the techniques developed for intelligent tutoring are applicable only in more structured settings, but fortunately there are other interesting opportunities to explore. In this paper we introduce a system called OurWeb, and use it as an exemplar framework for demonstrating some of these opportunities. We claim that effective participation in distributed and self-organizing collaboration requires suf- ficient awareness of the resources and dynamics of the community. The feasibility of implementing certain features of this kind is evaluated based on data from two university level courses. Keywords. collaborative learning environments, collaborative learning, collaborative annotation, awareness, social navigation, information retrieval 1. Introduction The objective of intelligent e-learning systems, as it is typically conceived, is to provide highly structured lessons that are to a large extent under automated control. Within this framework, the intelligence of the system often appears in the form of adaptive sequenc- ing or personalization of the course material, adaptive guidance for navigation, or inter- active problem solving support. All of these methods work the best in well-structured domains, and rely heavily on a fixed collection of pre-made course material. While the prevailing approach has arguably proved to be appropriate in several con- texts, there are good reasons to extend the perspective to other essential ways of learn- ing. On the one hand, the theoretical assumptions implicit in the instruction method have received substantiated criticism. Learning has been claimed to be primarily a matter of participation [1] or collaborative knowledge building [2] rather than direct assimilation of facts from an authoritative source. The critics have suspected that excessive guidance places the students in a passive role, hampers the development of metacognitive skills, and results in an instructional setting that is too simplified and restricted to facilitate real-world problem solving [3,4,5]. These claims may or may not be justified, but in any 1 Correspondence to: Miikka Miettinen, Helsinki Institute for Information Technology, P.O.Box 9800 FIN-02015 TKK, Finland; Tel.: +358 9 451 8123; E-mail: miikka.miettinen@hiit.fi. This work was supported in part by the Academy of Finland under the Prima and Prose projects.