Hacker Newsnew | past | comments | ask | show | jobs | submit | hntester123's commentslogin

Your comment reminds me of Google search, which is also quite simple in front (the UI/usage) and very complex under the hood.


Excellent comment, sir!


+1 on the parent-child thing.


>One thing that annoys me about software culture in general is how, by virtue of being a programmer, people are also political scientists, economists, biologists, chemists, astronomers, manufacturing experts, doctors, nutritionists, sociologists, anthropologists, and the grand poobah of dismissing speech because of the way it's phrased.

+N.


>You already have the data I'd use: the text of the comments.

Wouldn't that require real AI though? I thought for a minute that NLP (Natural Language Processing, not the other meaning(s) of the acronym) might help, but then thought that it may not work for cases where the comment is quoting another comment. Note: I'm not at all an expert in any of those fields, just interested.


Sounds like a job for Sentiment Analysis [1]. Modern systems are pretty good at discerning negative from positive comments.

You could probably find a way to mark negative and positive comments. Whether the resulting algorithm would be fine-grained enough to semi-reliably mark 'middlebrow dismissal,' I really don't know. Actually, as somebody who has worked on that stuff in the past, I don't think it would be very easy.

[1] http://en.wikipedia.org/wiki/Sentiment_analysis


Bing Liu is one of the researchers working on this. I've discussed Amazon review fraud detection with him. http://www.cs.uic.edu/~liub/


Thanks for the link.

Agreed I don't think it would be an easy task, but I wonder how would perform a "bag of word" approach.

Harder part as I see it would be to categorize the comments on middlebrow dismissal / Not dismissal. It seems like we would be spending more time preparing the data than in the algorithm itself.


Welcome to statistics/data science/machine learning.

The hardest part is always getting the data into usable form. Its not as much fun as fitting models, but its definitely the majority of any role where people pay you to do this kind of stuff.

There's a lot of good research on forums (pm me if you want a bibliography i collected for a previous role), and short texts have become a bigger deal post Twitter. I completely agree with pg on the somewhat annoying nature of comments such as the GP.


Hey... Thanks for the offer! How can I contact you? I didn't know we can pm users over here.

I did have worked with ML before but mostly with images which are (IMHO) way easier to put in a format depending on the problem.


My email is obsfuscated in my profile. Should be pretty clear, conditional on your humanity.


Hadn't heard of it; thanks for the link.


How about giving an acknowledgement on your page when someone submits a project / news? Did it a couple of times lately and saw nothing after the submit, even to show that the submission was received.


Hey there, sorry about that. Still a work in progress! I will see if I can get an intermediate page up there instead of redirecting back to the main page.

Thanks for the feedback!


Cool, thanks.


+1



Congrats on the site and thanks. As a guy interested in Go, I plan to check it out over time.


I really liked the Go Tour, which I checked out 3 weeks ago. Then I was a bit disappointed to see that the UI changed some, making it less user-friendly. (Everything used to fit on one page, except for longer examples, for instance.) Still like it overall, though.


Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: