KMi Seminars
MUP/PLE lecture series
This event took place on Tuesday 07 June 2011 at 14:00

 
Traian Rebedea “Politehnica” University of Bucharest

In most educational scenarios, the learners that use online discussions such as instant messaging and discussion forums never receive feedback for their conversations, especially due to the fact that such an analysis is very difficult and time consuming for tutors. This is the main problem that PolyCAFe is addressing by providing automatic feedback to learners and by supporting tutors in the analysis of their students’ multi-party online discussions.

PolyCAFe produces various kinds of information about discussions in chats and forums, both quantitative and qualitative, such as metrics (e.g. the relative importance of each utterance, learner grades both globally and for particular features like the involvement in the collaboration), and content analysis results (such as the coverage of the key concepts to be discussed and the discourse threads). PolyCAFe also provides visual feedback about the interactions and the social participation. The visualization of the conversations is interactive; that means the learners and tutors may explore different perspectives and discussion threads, they may view implicit links discovered by the system between utterances or posts and they may see the threading of using different concepts.

 
KMi Seminars
 

Multimedia and Information Systems is...


Multimedia and Information Systems
Our research is centred around the theme of Multimedia Information Retrieval, ie, Video Search Engines, Image Databases, Spoken Document Retrieval, Music Retrieval, Query Languages and Query Mediation.

We focus on content-based information retrieval over a wide range of data spanning form unstructured text and unlabelled images over spoken documents and music to videos. This encompasses the modelling of human perception of relevance and similarity, the learning from user actions and the up-to-date presentation of information. Currently we are building a research version of an integrated multimedia information retrieval system MIR to be used as a research prototype. We aim for a system that understands the user's information need and successfully links it to the appropriate information sources, be it a report or a TV news clip. This work is guided by the vision that an automated knowledge extraction system ultimately empowers people making efficient use of information sources without the burden of filing data into specialised databases.

Visit the MMIS website