26 comments

[ 2.7 ms ] story [ 67.6 ms ] thread
/me watched the "positive" side retweet a bunch of "every time i regain faith in humanity, someone spends more than 5 min in front of the ATM".
Pretty neat, though it looks like the sentiment analysis could use some work. There are quite a lot of negative ones on the positive side.

EDIT: Might be useful to expand this into a generic service where people can enter their own search terms.

Or allow page viewers to move something from one column to the other and have the back-end receive notification so that it modifies its sentiment algorithm automagically.
I see some positive ones on the negative side too:

"Batman no!! You can't lose your faith in humanity!"

"You must not lose faith in humanity. [...] - Gandhi"

I don't know how the sentiment analysis is being done (naive Bayes?), but perhaps it could be tweaked to handle this case.

Here is a stab in the dark:

These types of declaratives have two negatives side by side (e.g., "not lose", "can't lose"), making them into a positive. They're somewhat similar to rhetorical questions which have assertions embedded in them in the form of a negative question. From the Wikipedia article, "What have the Romans ever done for us?..." (What...ever...?) "...should be read as The Romans have never done anything for us"... (where a negative is surrounded by a verb).

http://en.wikipedia.org/wiki/Rhetorical_question#Negative_as...

What do people think of this? I'm not entirely familiar with naive Bayes classifier.

They'll be cancelled out by false positives, eg 'I try to maintain my my faith in humanity. Sometimes I succeed.'
Hi! Creator here, yes the sentiment analysis could definitely use more work but we've found our naiive approach to be about 95% accurate which was good enough for our MVP.

Definite idea, some friends have mentioned it might be useful for brands

This is a good start for sure, but as the previous readers mentioned it could use some work. Might consider looking for a series of keywords and adding removing positivity points based on their existance?
I can't help but lose a little faith in humanity when I see that faith in humanity is measured via Twitter.
Twitter is not the world or a meaningful representation of the world.
Buzzkill. You're making me lose faith in humanity. ;-)
Cool little weekend hack. Love the UI. It's a refreshing take on sentiment analysis.
Except that, for no good reason, it's awkward to read in a window narrower than the authors'. (Edit: and middle-click is broken.) I'd lose my faith in humanity, if I were persuaded that web developers are a subset.
If they include the common misspelling of "lose" as "loose" I suspect the good side won't have a chance.
I was toying around with the URL in some of the source and modified a few of the sources to be facebook rather than faithinhumanity. After a few tries, I got an interesting security message.

https://www.facebook.com/dialog/oauth?client_id=343797409063...

Wow! Really interesting, and weird. We aren't using anything Facebook-related besides the like button and we don't even have a registered Facebook app or secret keys or anything. All the Twitter sourcing is done on the server so I'm not sure how you stumbled onto that security message
Some are misclassified, such as "before I lose faith", or "else I will lost faith"
What was it I'm supposed to believe about humanity?
(comment deleted)
Imagine, people like to complain via hyperbole with twitter. #notsurprised
(comment deleted)