Feature extraction

We could potentially extract programming-related keywords from articles, but this might be stretch, and something we don't want to do initially, as it may reduce the number of true positives.

Still, the issue is open to discuss any ideas.

The issue names no files, tests, or entry points and presents keyword extraction only as a speculative idea. Start by reviewing how articles are currently processed, then establish whether the feature is wanted and how it would be evaluated; the issue does not currently define what done looks like.

Written by the indexing model from the issue text.