Archives for April 2017

End of Month Clearance Sale on Historical Twitter Data Access Using Sifter

April 25, 2017 by Stuart Shulman 15 Comments

From now until 5:00 PM EST April 30, 2017 we are offering a 30% discount on historical Twitter data access using Sifter. The discount will be applied directly to your estimate. We have made some other changes to simplify the process of generating estimates.

Fake News Detection Student Data Challenge Winners

April 17, 2017 by Stuart Shulman 1 Comment

We are pleased to announce the winners of the Fake News Detection Student Data Challenge:

First Place: UnderDogz
Second Place: CPO
Third Place: ULV Social

We want to thank everyone who participated. There is still a lot of work to be done in this area and we hope to involve more students in this sort of basic social data research over time.

Fake News Models: The Student Submissions

April 7, 2017 by Stuart Shulman Leave a Comment

Here are the submissions for our Fake News Detection student data challenge. We will announce the winners soon!

https://t.co/bkLGRbb1Ge #fakenewsdetection

— Sasha Chavez (@sashmchvz) April 2, 2017

We used Discovertext to identify the nature and scope of fake news. Check out what we found! https://t.co/t2rqVtrJTT #fakenewsdetection

— Joseph Heide (@Joseph_Heide) March 18, 2017

A model to describe the relationship between fake news and debunking practices @discovertext #fakenewsdetection https://t.co/DYevsXjvSr

— Alessio De Colle (@aldecolle) April 1, 2017

DiscoverText-Fake News Detection Challenge 2017https://t.co/eloYVwm26S #fakenewsdetection @StuartWShulman

— FONG WENG SHAO (@wengshao) April 1, 2017

Bots, Trolls, and Elections

Oh, Canada? A quick research note: your election is definitely under attack via Twitter, despite assertions to the contrary. This is part one of a nine-part series written in the run-up to the 2019 Canadian election. The research was reported by CTV and CBC. Twitter Data Collection on Canadian Elections For the last month, we […]

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.