Fraunhofer-Institut für Angewandte Informationstechnik FIT

Filters

13
9 4
Reset filters

Settings
Now showing 1 - 10 of 13
  • Publication
    Early results of experiments with responsive open learning environments
    ( 2011)
    Friedrich, M.
    ;
    Wolpers, M.
    ;
    Shen, R.
    ;
    Ullrich, C.
    ;
    Klamma, R.
    ;
    Renzel, D.
    ;
    Richert, A.
    ;
    Heiden, B. von der
    Responsive open learning environments (ROLEs) are the next generation of personal learning environments (PLEs). While PLEs rely on the simple aggregation of existing content and services mainly using Web 2.0 technologies, ROLEs are transforming lifelong learning by introducing a new infrastructure on a global scale while dealing with existing learning management systems, institutions, and technologies. The requirements engineering process in highly populated test-beds is as important as the technology development. In this paper, we will describe first experiences deploying ROLEs at two higher learning institutions in very different cultural settings. The Shanghai Jiao Tong University in China and at the "Center for Learning and Knowledge Management and Department of Information Management in Mechanical Engineering" (ZLW/IMA) at RWTH Aachen University have exposed ROLEs to theirs students in already established courses. The results demonstrated to readiness of the technology for large-scale trials and the benefits for the students leading to new insights in the design of ROLEs also for more informal learning situations.
  • Publication
    Demands of modern PLEs and the ROLE approach
    ( 2010)
    Kirschenmann, U.
    ;
    Scheffel, M.
    ;
    Friedrich, M.
    ;
    Niemann, K.
    ;
    Wolpers, M.
  • Publication
    Usage-based object similarity
    ( 2010)
    Niemann, K.
    ;
    Scheffel, M.
    ;
    Friedrich, M.
    ;
    Kirschenmann, U.
    ;
    Schmitz, H.-C.
    ;
    Wolpers, M.
    Recommender systems are widely used online to support users in finding relevant information. They can be based on different techniques such as content-based and collaborative filtering. In this paper, we introduce a new way of similarity calculation for item-based collaborative filtering. Thereby we focus on the usage of an object and not on the object's users as we claim the hypothesis that similarity of usage indicates content similarity. To prove this hypothesis we use learning objects accessible through the MACE portal where students can query several architectural repositories. For these objects, we generate object profiles based on their usage monitored within MACE. We further propose several recommendation techniques to apply this usagebased similarity calculation in real systems.
  • Publication
    A framework for the domain-independent collection of attention metadata
    ( 2010)
    Scheffel, M.
    ;
    Friedrich, M.
    ;
    Niemann, K.
    ;
    Kirschenmann, U.
    ;
    Wolpers, M.
  • Publication
    Introducing a social backbone to support access to digital resources
    ( 2010)
    Memmel, M.
    ;
    Wolpers, M.
    ;
    Condotta, M.
    ;
    Niemann, K.
    ;
    Schirru, R.
  • Publication
    Connecting contents in distributed repositories through the use of real world objects
    ( 2010)
    Niemann, K.
    ;
    Wolpers, M.
    The MACE project provides advanced graphical metadata-based access to learning resources in architecture. Through the digital representation of real world objects in our system, we are able to bridge the various repositories of architectural learning material and facilitate graphical information retrieval. In order to create the real world object representations, we apply advanced information retrieval technologies that ensure a high precision. We outline the generation and usage of real world object representations within the MACE system and present the results of the evaluation of our approach.
  • Publication
    Nutzbarkeit dynamischer Umgebungen für autonomes Lernen
    ( 2010)
    Kirschenmann, U.
    ;
    Schmitz, H.-C.
    ;
    Wolpers, M.
    ;
    Dreusicke, M.
    Self-regulated learning burdens the learner with configuring his own individual learning environment. The task is hard to accomplish; learners might need help. We define two means to this end, namely context-sensitive recommendations and data analyses for reflection support. Both means are based on the recording and analysis of usage data. We introduce the CAM (Contextualized Attention Metadata) schema as a format for such usage data and describe how CAM can be recorded and exploited locally or on remote servers. As examples we refer to two hypermedia learning systems, namely MACE and PAUX.
  • Publication
    Early experiences with responsive open learning environments
    ( 2010)
    Wolpers, M.
    ;
    Ullrich, C.
    ;
    Renzel, D.
    ;
    Friedrich, M.
    ;
    Klamma, R.
  • Publication
    Responsive open learning environments for computer-assisted language learning
    ( 2010)
    Scheffel, M.
    ;
    Schmitz, H.-C.
    ;
    Shen, R.
    ;
    Ullrich, C.
    ;
    Wolpers, M.
    Responsive open learning environments (ROLEs) compile contents and services in such a way that service widgets can communicate with each other. ROLEs thus enable existing learning management systems to enhance their learning offers which in turn become part of the ROLE. As a technical proof of concept we - by means of a language learning prototype developed as a technical proof of concept in the context of the European project ROLE - first show how interoperability of widgets can be achieved and then present how the implementation of language learning widgets into a running learning environment at the Shanghai Jiao Tong University in China serves as an institutional proof of concept for the applicability and acceptance of ROLEs.
  • Publication
    Issues and considerations regarding sharable data sets for recommender systems in technology enhanced learning
    ( 2010)
    Drachsler, H.
    ;
    Bogers, T.
    ;
    Vuorikari, R.
    ;
    Verbert, K.
    ;
    Duval, E.
    ;
    Manouselis, N.
    ;
    Beham, G.
    ;
    Stern, H.
    ;
    Lindstaedt, S.
    ;
    Friedrich, M.
    ;
    Wolpers, M.
    This paper raises the issue of missing data sets for recommender systems in Technology Enhanced Learning that can be used as benchmarks to compare different recommendation approaches. It discusses how suitable data sets could be created according to some initial suggestions, and investigates a number of steps that may be followed in order to develop reference data sets that will be adopted and reused within a scientific community. In addition, policies are discussed that are needed to enhance sharing of data sets by taking into account legal protection rights. Finally, an initial elaboration of a representation and exchange format for sharable TEL data sets is carried out. The paper concludes with future research needs.