Tom, thanks for the link. I've been to the site in the past. I just
revisited, and entered "Sarah Palin" in the search box. It returned 50
tweets, labeled 39 as neutral, 5 positive and 6 negative. I checked
the actual tweets, and here's what I found:
- Neutral: I only found one (maybe). The other
http://tweetsentiments.com uses Machine Learning and NLP for sentiment
analysis.
No published API access yet(some already available), but it's on the
road map.
Currently sacrificing some precision for speed, but we will focus on
improving precision in the near future.
Based on the search keyword "tude" and what follows it: (, ) or ?, I
made the same guess myself, but I did not want to assume anything.
Interesting link. I used to do some of that to analyze posts on a
forum in the early days of the internet (to weed out impostors), but
it did not work well.
On J
On Jul 22, 8:49 pm, Joseph wrote:
> That's what I meant. Short of doing a search, with tude[]=%3A) and
> store it in my cache (which will eat up a lot of API calls), do you
> have any hints on how to extract this out of the API?
Isn't it just searching for the Strings ":-(", ":-)" and "?"? I don
That's what I meant. Short of doing a search, with tude[]=%3A) and
store it in my cache (which will eat up a lot of API calls), do you
have any hints on how to extract this out of the API?
Thanks,
Joseph
On Jul 22, 10:52 am, Doug Williams wrote:
> Joseph,I assume you mean the sentiment portion
Joseph,I assume you mean the sentiment portion of the Search API? That is
not available as structured data through an API call.
Thanks,
Doug
On Wed, Jul 22, 2009 at 3:36 AM, Joseph wrote:
>
> Is the attitude (tude) flag stored as part of a tweet? and if so, do
> any of the data structures re