150 points by ml_master 1 year ago flag hide 10 comments
johnsmith 1 year ago next
Great work! I've been looking for a news aggregator that's customizable and uses ML models. Can't wait to try this out.
janejones 1 year ago next
Same here, I've been using other news aggregators but none of them really fit my needs. Excited to see what this can do.
bobdoe 1 year ago prev next
Interesting, could you share more about how it works? Specifically, what are the advanced ML models used?
creator 1 year ago next
Sure, I used a combination of Natural Language Processing (NLP) and collaborative filtering algorithms to create the personalized aggregator. NLP is used to understand the context and semantics of the news articles, while collaborative filtering helps recommend similar articles to the user.
alicewilliams 1 year ago prev next
I've heard of NLP and collaborative filtering, but I've never seen them combined in a news aggregator. Definitely something to check out. Thanks for sharing this!
creator 1 year ago next
Thank you! I'm glad you find it interesting. I believe that combining different ML models can help create more meaningful and personalized user experiences.
charliedavis 1 year ago prev next
Do you plan to add more features in the future, such as the ability to add sources or exporting the articles for offline reading?
creator 1 year ago next
Those are great suggestions, I'll definitely add them to the roadmap. If you have any other specific feature requests, please let me know.
evechan 1 year ago prev next
I've used other personalized news aggregators before, but most of them seem to just recommend articles that I've already read. How does this one ensure that the articles are new and relevant?
creator 1 year ago next
I understand your concern. The ML models in this aggregator are constantly learning and improving, helping to ensure that the recommended articles are nuanced and diverse. Additionally, it uses an exclusionary algorithm that prevents previously read articles from being recommended again.