_____________________________________________________________________
SUMMARY
MUCKE seeks to address the rapid proliferation of multimedia social data under the rubric of Web 3.0 by designing new and reliable knowledge extraction models which will be specifically calibrated for multilingual and multimodal data shared on social networks.
The project departs from current knowledge extraction models, which are mainly quantitative, by attaching a high importance to the quality of the processed data, in order to introduce the possibility of qualitative distinction and preference within vast quantities of topic-homogeneous data.
_____________________________________________________________________
SOLUTIONS
- Developing an automatised user credibility model for establishing the credibility of user-generated data sources
- Creating a semantic representation of the underlying data structures and assigning a probabilistic framework to them.
- Introducing new models for processing noisy multimodal and multilingual data that will constitute the base for innovative services.
_____________________________________________________________________
LINK: https://tiss.tuwien.ac.at/research/project.xhtml?projectId=213457
_____________________________________________________________________
