Live data from Hacker News

Show HN: Hacker News with categories and popularity

newshack.io

41–50 of 68 posts

Re: Show HN: Hacker News with categories and popularity

#42
post #35

Earlier quoted context omitted.

I am planning to open source it in several months. (Our codes have not been well-commented and well-structured yet... Our implementation and algorithm detail is followings. Its categorizing process is written in Python. Using nltk, it makes corpus with TFIDF model from HN topics and comments. And it generates classifiers from this corpus with SVM algorithm using scipy and numpy. FYI, its web interface is written in C…

presumably you've trained it with hand annotated content, or bootstrapped from a few choice hn searches (like ?q=jquery will give you a web tech category)

Yes. You are right.

I trained classifiers with hand annotations (about 1000 contents or so)

Re: Show HN: Hacker News with categories and popularity

#45
It's a sad commentary on the current demographics here that there is no "entrepreneur" category at all. And that the next closest thing, "business" has only 3 articles, none of which are related to running a business.

I'd noticed myself finding less and less to click on on the front page over the last year, but this has really driven home why.

Re: Show HN: Hacker News with categories and popularity

#46

Earlier quoted context omitted.

Isn't that just news.ycombinator.com?

Nope, I see NSA news every other day on HN and it is getting rather annoying

Supposedly there is a filter already on HN for NSA articles, each vote only counts as 1/3 of a vote if the title contains the string "nsa", severely penalizing those articles.

Re: Show HN: Hacker News with categories and popularity

#48
It would be useful if each article could have its tag displayed. In that way when looked at "all" I could start to get an idea of what the tags mean to the system. At the moment I'm reasonably often finding things tagged other than I would expect. Showing tags next to items would help me recalibrate.

Other than that - good job. Thank you.

Re: Show HN: Hacker News with categories and popularity

#49
Very useful! Would be good if you could adjust the time-range with respect to the category i.e. for a popular category, 1 day of news is great but something like jokes - currently there's just an empty page - http://newshack.io/by-categories?category=9&term=day - here a month is more interesting - http://newshack.io/by-categories?category=9&term=month

Re: Show HN: Hacker News with categories and popularity

#50
post #2

Very nice. How you determine categories?

Using natural language processing and supervised learning, it automatically tagged news with 9 categories.

I wonder if you clustered HN articles to find categories automatically. That may not be useful, but I'd be interested in seeing how HN articles are naturally categorized.
Post reply on HN