Bib Tutor

Development of an electronic tutor system for information retrival

Development of an electronic tutor system for information retrival

  • Duration:

The ability to deal with information in a reasonable and active way is today just as important as reading, writing and basic arithmetic. The teaching of this competence in connection with the navigation of information sources is the goal of the project BibTutor, started on 1 November 2004 with a duration of 2 œ years. This project is supported by the Federal Ministry of Education and Research (BMBF) with a budget of approximately one million euros and coordinated by the German Research Center for Artificial intelligence (DFKI) in Kaiserslautern.

Courses teaching competence in the field of information retrieval, as offered by scientific libraries, have proved inadequate for several reasons. They are tied to locations and, due to staff reasons, are not sufficiently optimized to specific fields and tasks. Unfortunately they are also unavailable when a specific information requirement arises - for example, if the content of a recently attended lecture should be further investigated or if one has to write a seminar paper. The project BibTutor pursues here a completely novel concept. Navigation tools for information sources are to be expanded so that they integrate closely with the traditional search such that they support the selforganized acquisition of knowledge and put the traditional search into the current context of the information requirement.

The planned BibTutor system is designed to help the library visitor during the selection of a suitable information sources, as selecting among the great number of the available catalogs and databases can be a problem. During the actual research in the information sources the BibTutor system takes the place of a mentor which gives concrete recommendations - for example, if an inquiry supplies too many, too few, or even no answers, or the result does not otherwise correspond to the user?s expectations. This is realized with the usage of modern text mining technologies which derive, for example, semantic similarities between ad-hoc search keywords and the default keywords in the information sources in a stand-alone way.


brainbot technologies AG, TU Kaiserslautern, TU Hamburg-Harburg , TU Darmstadt, Universität Heidelberg

Publications about the project

Thomas Hapke, Martin Memmel

In: Marlies Ockenfeld (editor). Proceedings der 28. Online-Tagung der DGI. Online-Tagung der Deutsche Gesellschaft für Informationswissenschaft und Informationspraxis (DGI) Frankfurt am Main Pages 123-133 Tagungen der Deutschen Gesellschaft für Informationswissenschaft und I 8 Deutsche Gesellschaft für Informationswissenschaft und Informationspraxis 2006.

To the publication

German Research Center for Artificial Intelligence
Deutsches Forschungszentrum für Künstliche Intelligenz