Hello folks. I'm Jen. Just moved to SF from Scotland where I ran a data
intelligence startup which dug into Twitter sentiment analysis (see
festbuzz.com for an example).
I'm consulting, writing, speaking and doing a day job at a Silicon Valley
tech co. for now, but I have a list as long as my arm
If you're new to NLP, I recommend getting a book like Natural Language
Processing with Python, using the Python Twitter API, and writing a Bayesian
spam classifier. If you're less new, I've been working in sentiment
classification for a while now and it's a lot of fun. Also things like
automaticall
doing the whole 'people vote other tweets up/down manually'
thing; it's such a jump to get that level of user interaction frequently
enough to be meaningful.
-J
--
Jennie Lees
Founder, Affect Labs
jen...@affectlabs.com
http://twitter.com/jennielees
On Sun, Jul 19, 2009 at 12:02 AM, M. Edward (Ed) Borasky
wrote:
> Man, it is so good to hear this from someone who's actually done it!
> The other point, though, is that the "real thing", even traffic /
> social network analysis, is compute-resource intensive and requires a
> kind of programming k
TweetDeck (http://www.tweetdeck.com) is the obvious answer, you can group
your contacts into different panels and thus not have the noisy drown out
the intelligent.
Pretty sure other clients do it too, to different extents - a bit of
googling and trying them out won't hurt if TD's not to your liki
/blog/about
> >
> > I know a 409 should mean timed out... but the response comes back in
> > one second (or just really really fast).
> >
> > Any help appreciated...
> >
> > Brian Roy
> >
> > justSignal
>
--
Jennie Lees
Founder, Affect Labs
jen...@affectlabs.com
http://twitter.com/jennielees
Hi all,
I'm looking for a way to find the number of tweets matching a certain
term, both overall and as a time series (e.g. how many results between
11:00 and 12:00 - I want to monitor changes over time).
I can't really see an obvious way to do this beyond making a local
copy of every tweet and
this would be close to fitting your needs, but something
> to start with maybe...
> -Chad
>
> On Mon, Feb 9, 2009 at 10:52 AM, Jennie Lees wrote:
>>
>> Hi all,
>>
>> I'm looking for a way to find the number of tweets matching a certain
>> term, both
ed list, gets recent updates for these
accounts, then posts said updates to its own account with a bit of "RT @foo"
added. You can cut off messages since a particular id or time to ensure you
don't duplicate etc etc.
j
--
Jennie Lees
Founder, Affect Labs
jen...@affectlabs.com
http://twitter.com/jennielees
s a change in the API which
> renders the python function obsolete?
>
> I would appreciate any help with this.
>
--
Jennie Lees
Founder, Affect Labs
jen...@affectlabs.com
http://twitter.com/jennielees
10 matches
Mail list logo