Knowledge graph

Every headline in the feed is reduced to its keywords. A node is a keyword; an edge means two keywords showed up in the same article, and the thicker it is the more often that happened. Drag nodes, tune the thresholds, and click any node to read the articles behind it.

— nodes — edges 466 articles 5279 distinct terms

Find a topic

Max nodes 60

How many of the most frequent keywords to draw.

Min mentions 2

Drop keywords seen in fewer articles than this.

Min co-occurrence 2

Hide weak links between keywords.

Neighbourhood depth 1

When a node is focused, how many hops out to keep.

Always show labels Include unconnected nodes

Reading it

Node size is how many articles mention the keyword. Edge thickness is how often two keywords share an article. Colour groups the clusters the layout pulls apart.

Building the graph…

Keywords are extracted with a stopword filter, so ordinary English and newsroom filler ("says", "report", "according") never become nodes. Phrases are preferred over single words where both occur, which is why you see language model rather than language and model as separate topics.

Knowledge graph

Not enough data yet

—