M-Brain published a “next-generation” visualisation demo in the website. Dataset is a random sample from a multilingual web slice containing the named entity "Barack Obama". You can get a picture of the relevant articles more easily.
Visualisation layout is calculated according to conceptual distance between each document pair. Similar documents are grouped together and different ones are placed apart. It’s easier to find common themes and other similarities between different Obama articles.
Click here to see the demo!