• A project with DIFID and SEI looking at the mapping between topics and locations of research papers.
  • Duration: 2 weeks
  • CEMAC Output –  To create an interactive web interface to visualise existing natural language processing work. 
  • Project URL: https://cemac.github.io/DIFID/ui/


As part of the DIFID project papers are fed into a NLP algorithm to generate a set of weighted topics. Plotting these as a graph we can see that topics tend to be grouped in a scale-free graph structure.

Using a dimensionality reduction algorithm (t-SNE), it is possible to achieve much the same result, displaying like-papers together. This is shown as part of the DIFID app at the link above.

Within this we can also display items geographically.


Summary – 

The CEMAC role was to provide guidance and produce an interactive app with the following criteria:

  • Visualise the global positions of each paper and study location
  • Visualise the dimensionality reduced grouping of items
  • Interactive zoom, item identification and filtering
  • Selecting individual continents
  • Filtering using a hierarchical topic tree
  • Slider to isolate items with only strong relationships to a topic
  • Linking data points to a download link for each paper
  • Fuzzy matching for relevant papers
  • Intuitive non-obfuscated region identification (using the t-SNE dataset)
  • Using data within the format provided (no pre-processing)
  • Potential scalability – the visualisation needs to still be responsive with millions of datapoints.



Skills Used

node js html css