Chaohai Ding and Yunjia Li (University of Southampton) have enriched the Talk of Europe dataset in several ways during the first creative camp. Please visit this website for a demonstration of their work.
- Look into the data (dump the data locally using 4store to host the RDF);
- Enrich the data (use the NLP tools to extract the topic, sentiments and summaries of the debates);
- Write back to the data set real time (use SPARQL 1.1 to update the local store by using lp:cate, lp:sentiment and lp:sum);
- Data Visualization (D3.js, Leaflet.js, Node js);
- From 4-star Linked Data to 5-star Linked Data (add owl:sameAs to other resource on the Web);
- Future work: mining the data with background of MPs and see how do they make decisions.