CARSA - A Context Adaptive Retrieval System Architecture

CarsaInformation retrieval systems serve as mediators between the user interests on one side and the raw text or multimedia data stored in data collections on the other side. However, current retrieval systems hardly consider the background knowledge of a user or the context he is searching in. For example, web search engines provide the same results to every user, neglecting his interests or the way he is used to sort and structure information. CARSA is a web services based architecture, which supports the development of context based information retrieval systems. The idea of these systems is to support a user in his search process by, e.g., adapting the search results as well as the interface itself to user specific needs and interests.

CARSA's data and programm structure was designed based on web services and XML. This allows to easily integrate and combine different methods to search data locally or on the web (meta-searcher functionality), to modify or categorize search results, and to develop visualization methods on diverse clients (e.g. desktop PCs or mobile devices). In addition, CARSA contains a testing environment for evaluating single methods, e.g. classification or clustering methods, or their combinations with standard performance measures on benchmark data sets.

Related Publications:

  • Korinna Bade and Andreas Nürnberger, Personalized Structuring of Retrieved Items, In: Proc. of the Workshop on Personal Information Management, 2006.
  • Korinna Bade, Ernesto W. De Luca, Andreas Nürnberger, and Sebastian Stober, CARSA - An Architecture for the Development of Context Adaptive Retrieval Systems, In: Proceedings of the 3rd International Workshop on Adaptive Multimedia Retrieval, 2005.
  • Korinna Bade and Andreas Nürnberger, Supporting Web Search by User Specific Document Categorization: Intelligent Bookmarks, To appear in: Proceedings of LIT2005, 2005.
  • Ernesto W. De Luca and Andreas Nürnberger, A Meta Search Engine for User Adaptive Information Retrieval Interfaces for Desktop and Mobile Devices, In: Proc. of the PIA 2005 - Workshop on New Technologies for Personalized Information Access, Edinburgh, Scotland, UK, 2005.
  • Ernesto W. De Luca and Andreas Nürnberger, Supporting Mobile Web Search by Ontology-based Categorization, In: Sprachtechnologie, mobile Kommunikation und linguistische Ressourcen. Beiträge der GLDV Tagung 2005 in Bonn, S. 28 - 41, 2005.
  • Ernesto W. De Luca and Andreas Nürnberger, Improving Ontology-Based Sense Folder Classification of Document Collections with Clustering Methods, In: Proc. of the 2nd Int. Workshop on Adaptive Multimedia Retrieval (AMR 2004), pp 72-86, Valencia 2004.

Public Presentations

  • CeBIT 2005, 2007 und 2008
  • Web Intelligence Konferenz 2006 in Hong Kong

If you are interested in using our system, either as a user performing a search or as a developer in the field of information retrieval, send an email to

Last Modification: 01.03.2018 - Contact Person: