A4MC3

Architectures for Mobile Community Content Creation

Aim

The aim of the A4MC³-IBBT project is to explore the possibilities of community building using state of the art technology, mobile terminals, wireless networks, multimedia and meta-data technology to create a new, friendly experience.

Partner

In this project we have worked closely together with Concentra Media, Hasselt .

Results

The contribution of the LIIR research group is twofold. First, it has normalized dialect words to their equivalent in standard Dutch language, second it has clustered the noisy texts into topic hierarchies, where a co-clustering approach (jointly clustering terms and documents) was evaluated. The detected topics serve as meta-data to the texts.

For the legal research conducted on the same project, please visit relevant page



Period From 2005-06-01 to 2007-05-31.
Financed by IBBT
Supervised by Marie-Francine Moens
Staff Wim De Smet
Contact Wim De Smet

More information can be found on the project website http://www.ibbt.be/nl/project/a4mc3-0

Publications

  1. DE SMET, Wim and MOENS, Marie-Francine Extraction of Folksonomies from Noisy Texts. In Proceedings ICWSM International Conference on Weblogs and Social Media, March 26-28, 2007, Boulder Colorado, USA (pp. 299-300). Omnipress. 2007
  2. DE SMET Wim and MOENS, Marie-Francine. Generating a Topic Hierarchy from Dialect Texts. In Proceedings of the 4th International Workshop on Text-based Information Retrieval (TIR-07) . IEEE Computer Society. 2007


Back to all projects