[Air-L] Software to extract content of Facebook & Twitter

Shulman, Stu stu at texifter.com
Wed Aug 27 03:52:50 PDT 2014


DiscoverText has been connected to the Facebook Open Graph API and the
Twitter Search API since 2010. Here are some reasons to test it for
collecting Facebook or other social and related non-social data:

- there is nothing to install - use it in a browser
- pull data in from a variety of sources, including SurveyMonkey directly
via an API
- keystroke human coding is fast and connects to other human coders via a
peer network
- measurement tools developed open source in 2007 for inter-rater
reliability and adjudication of coder disagreement (CAT)
- search, filtering, and bucketing capabilities
- automated duplicate detection and near duplicate clustering
- machine learning classifiers that help sift out irrelevant data to
'clean' social data sets
- patent pending "CoderRank" technology for enhanced machine-learning
- free for the first 30 days
https://www.discovertext.com/Home/TrialRegistration

We are also in the last week of the final drawing to win 1,000,000
historical Tweets and a year's worth of Enterprise grade software worth
more than $15,000. It takes about five minutes to beta test the free
historical Twitter estimator "Sifter" (http://sifter.texifter.com) and then
enter: http://bit.ly/1pGuUJo.

These are high-grade tools for text and metadata developed in a research
lab specifically to improve measurement.




On Wed, Aug 27, 2014 at 3:41 AM, Cristina Aced <blogocorp at gmail.com> wrote:

> Hello all,
>
> I am looking for software that facilitates the extraction of content of
> Facebook pages. I am doing a research about how a sample of companies are
> using blogs, Twitter and Facebook. I want to apply content analysis but
> previously I need to extract the content.
>
> I am using R and the software OutWit Hub Pro to scrape the data on blogs
> and Twitter, but they are not working properly with Facebook (I think it is
> due to some restrictions of Facebook's API).
>
> Any other suggestions?
>
> Many thanks!
>
> *Cristina Aced *
> PhD Candidate
> Doctoral Programme in Knowledge and Information Society
> Universitat Oberta de Catalunya
> | caced at uoc.edu
> www.cristinaaced.com/blog | Twitter: @blogocorp
> _______________________________________________
> The Air-L at listserv.aoir.org mailing list
> is provided by the Association of Internet Researchers http://aoir.org
> Subscribe, change options or unsubscribe at:
> http://listserv.aoir.org/listinfo.cgi/air-l-aoir.org
>
> Join the Association of Internet Researchers:
> http://www.aoir.org/
>



-- 
Dr. Stuart W. Shulman
http://people.umass.edu/stu

Founder and CEO, Texifter
http://texifter.com

LinkedIn
http://www.linkedin.com/in/stuartwshulman

Twitter
https://twitter.com/StuartWShulman



More information about the Air-L mailing list