I’m using Feedly (google reader clone) to keep track of my news. However, there are tons of duplicates (same event/topic different sources).

I was just thinking about using text summaries + similarity analysis (possible AI driven) to cluster groups of articles. Are there already solutions for that? I could build it myself, but I’m not exactly the best web dev.

  • AggressivelyPassive@feddit.deOP
    link
    fedilink
    English
    arrow-up
    1
    ·
    1 year ago

    That’s pretty much, what I hoped for, but too closed for my taste. I can’t define my own feed to summarize, for example.

    (and I don’t get any German news, which is a bummer if you actually live in Germany)

    • oldfart@lemm.ee
      link
      fedilink
      English
      arrow-up
      1
      ·
      1 year ago

      I actually wrote to the author, not being from the US too, and they said they are working on a version where you can specify your country/location. Nothing about adding your news sources, though

      • AggressivelyPassive@feddit.deOP
        link
        fedilink
        English
        arrow-up
        2
        ·
        1 year ago

        As I wrote in the update above, I might just write it myself, it seems surprisingly easy given the availability of pretrained models.

        How fast that will be in practice is another question.