Validating Interaction Filters with Facebook Super Public Text Samples
DataSift PYLON for Facebook Topic Data allows you to analyze audiences on Facebook whilst protecting users' privacy. To help you build more accurate analysis we're introducing 'Super Public' text samples for Facebook. You can use Super Public text samples to validate your interaction filters to check you are recording the correct data into your index for analysis. You can also use these text samples to train machine learned classifiers. In this post we'll take a look...
Read Validating Interaction Filters with Facebook Super Public Text Samples
Building Better Machine Learned Classifiers Faster with Active Learning
You might have seen our recent announcement covering many things including the announcement of VEDO Intent. You're probably aware that DataSift VEDO allows you to run machine-learned classifiers. Unfortunately creating a high-quality classifier relies on a good quantity and quality of manually classified training data (which can be a painstaking task to produce) and exploration of machine learning algorithms to get the best possible result.
VEDO Intent is a tool that helps...
Read Building Better Machine Learned Classifiers Faster with Active Learning
Exploring Keyword Relationships in Social Posts with word2vec
You might have seen our recent announcement covering many things including the launch of our new FORUM data science initiative. We're looking to share more of our experience and research to help innovation in social data analysis.
One of the first things we wanted to share is our work exploring the relationships between keywords and terms in social posts. Our data science team has been researching this area using word2vec - a data science library that models the relationship / similarity...
Read Exploring Keyword Relationships in Social Posts with word2vec
How To Update Filters On-The-Fly And Build Dynamic Social Solutions
It would be easy if the world around us was static, but in practice things are always changing. Nowhere is this truer than in the world of social networks; users are constantly following new friends and expressing new thoughts. The filter you wrote yesterday is probably already out-of-date!
On the DataSift platform you can update your filters on the fly via the API and avoid downtime for your application. This not only allows you to adapt to real-world changing scenarios,...
Read How To Update Filters On-The-Fly And Build Dynamic Social Solutions
Facebook Pages Managed Source Enhancements
Taking into account some great customer feedback, on May 1st, 2014 we released a number of minor changes to our Facebook Pages Managed Source.
Potential Breaking Changes
Facebook Page Like and Comment Counts have been Deprecated
The facebook_page.likes_count and facebook_page.comment_count fields have been deprecated from DataSift's output. We found this data became outdated quickly; a better practice for displaying counts of likes and comments in your application is...
Read Facebook Pages Managed Source Enhancements