DiscoverText

Archives for October 2015

Week 2 Winners

by Leave a Comment

Congratulations to the second round of winners in our historical Twitter giveaway. Each week we are picking up the tab for two people to explore up to 100,000 Tweets pulled from up to 10 historical Twitter days. To learn more and enter the drawing, read the original blog post. 

 

Discovertext now has 70 scholarly mentions

by 2 Comments


“DiscoverText made it possible for us to capture, map and deconstruct online political talk about the European Union found in a variety of online sources: Twitter, Facebook, political blogs, forums and online news platforms.” – Dr. Asimina Michailidou, Senior Researcher at the ARENA centre for european studies, University of Oslo

Discovertext is an important tool for researchers to streamline their data collection in order to quickly and accurately make better decisions.  Two recent articles by Jill Hopke titled Hashtagging politics: Transnational anti-fracking movement Twitter practices, and ” Discourse over a contested technology on Twitter: A case study of hydraulic fracturing” mean that Discovertext has hit 70 scholarly mentions! See the full list of scholarly mentions with links. This is a trove of information for students needing to write up their methodology in a lit review for a paper or thesis.

As an appreciation, we will be interviewing influential academic users who have used Discovertext in their research.  We will be seeking information on how they use Discovertext, why they use it, and their favorite features.  

If you are interested in searching and retrieving data from the complete history of Twitter we are holding a series of drawings that will give away Historical Twitter days, Tweet data credits, and Enterprise account access to Discovertext. 

 

 

New Historical Twitter Prizes

by Leave a Comment

Win Historical Twitter Data with Easy Steps

Last year, we held a series of drawings that gave winners Historical Twitter days, Tweet data, and Enterprise account access to DiscoverText. Some of the winners have gone on to do amazing and influential work on the methods and tools used to research Twitter. As a result, we now list 70 scholarly mentions of DiscoverText.

So, brace yourself folks, because in honor of #TwitterFlight, we are doing it again this year and instead of once a month we will draw two winners on Fridays every week for the remainder of 2015. The prize for each winner is ten free Historical Twitter days, 100,000 Tweet credits, and three-months of Enterprise access to DiscoverText.

​There will be a weekly drawing of two winners at random. The prizes will be drawn every Friday morning, starting on October 23. The contest will be held every week for the rest of 2015. You have many chances of winning, with a limit of one prize per unique Twitter handle during 2015. Are you ready to win some prizes? Here is a step by step guide on how to enter the contest.

  • Step #1. Test Sifter. You can test Sifter by submitting a valid estimate. Sifter is a free estimate service provided by Texifter that allows you to test query rules (as well as the ability to filter and retrieve data for a fee) from the complete, undeleted history of Twitter. Powered by Gnip.com, it estimates the number of Tweets responsive to the query and the cost of the retrieval.  Read what past customers have said about Sifter and register for a free account.
  • Step #2. Submit your entry as a Tweet. When you submit your entry, include the link sifter.texifter.com, as well as a <140-character review of the product. Do not forget the URL. Only one entry per Twitter ID is allowed per drawing, but those of you with more than one Twitter handle can submit multiple entries.
  • Step #3. Wait for the announcement of winners. The winners will be drawn every week starting on October 23. Check the Texifter blog to find out if you are one of the lucky winners. Of course we will Tweet about it too.

Are you excited? We definitely are! By testing Sifter’s powerful capabilities, you get a chance to win 10 Historical Tweet days, 100,000 Tweets and 3-month Enterprise access to DiscoverText, which includes one Enterprise account and two Professional accounts. Find out if Sifter and DiscoverText are right for you and win these amazing prizes without spending a penny. We want your social currency.

  • Ten Historical Twitter Days & 100,000 Tweets: Winners need to collect their prize within seven days of the announcement.
  • Two Professional Accounts: The Professional account, which regularly costs $99/month, includes 100,000 units of social or text data from any source, 25 live data feeds, one professional seat and unlimited projects. It features analytic and reporting tools, adjudication tools, CloudExplorer, and standard support.
  • One Enterprise Account: The Enterprise account, which costs $3,000 a month, includes 1,000,000 units of social or text data from any source, 100 live data feeds, two professional seats, one enterprise seat, and unlimited projects. It includes all Professional features plus ActiveLearning, FOIA toolkit access, and priority support.

For more information about Texifter’s social data offer and our advanced analytical tools, please email us at info@texifter.com. 

 

 

Boolean defined search, n-grams, word clouds, and custom topic dictionaries

Power tools for text analysis and machine-learning

Discover central topics and also elusive but valuable unexpected or rare concepts. Use this information to train machine-learning classifiers to recognize relevant text and social media data. Jump into data using an interactive word CloudExplorer or build a mini topic dictionary using “defined” search. Try our new CloudExplorer listview for seeing the top 300 bigrams or trigrams in your data. Merge or delete terms as part of building your custom text analytics model.

DiscoverText is powered by uClassify

Machine-learning for everyone

Create gold standard training sets by labeling your training data accurately and reliably using our state-of-the-art collaborative annotation system. Then use our trusted, multilingual machine learning web service (uClassify) to create and apply your own custom-trained text classifiers. Please take the time to check out the work being done by the large and growing uClassify community.