New Academic Citations of DiscoverText: 2019-2020
DiscoverText | Machine-learning on text and Twitter data
by Stuart Shulman
4y ago
New Academic Citations of DiscoverText: 2019-2020 Communication About Hereditary Cancers on Social Media: A Content Analysis of Tweets About Hereditary Breast and Ovarian Cancer and Lynch Syndrome https://link.springer.com/article/10.1007/s13187-018-1451-4 The Story of Goldilocks and Three Twitter’s APIs: A Pilot Study on Twitter Data Sources and Disclosure https://www.mdpi.com/1660-4601/17/3/864 Free and Low-Cost Twitter Research Software Tools for Social Science https://journals.sagepub.com/doi/abs/10.1177/0894439320904318 VATAS: An Open-Source Web Platform for Visual and Textual Analys ..read more
Visit website
Top 100 Most Viral Tulsi OR Gabbard Tweets
DiscoverText | Machine-learning on text and Twitter data
by Stuart Shulman
4y ago
Just a quick video research note from the field. Contact us to join the effort to better understand how Twitter amplifies certain political actors via a variety of platform affordances. Find out why academics trust us to support theair collaborative, multilingual, multidisciplinary research ..read more
Visit website
Trump Trolls and Tulsi2020
DiscoverText | Machine-learning on text and Twitter data
by Stuart Shulman
4y ago
The New Normal: Tulsi2020 Have you ever fallen into a spiraling lake of data? That is how it feels trying to understand the debate between Hillary Rodham Clinton and Tulsi Gabbard over the “Russia” question. In the last post, we alerted readers to the heavy presence of #MAGA movement identities (user_descriptions) in the “Tulsi OR Gabbard” Twitter data which is accumulating at a remarkable rate. Today, while we are pouring over the translated Russian and other non-English user bios, I wanted to share something new emerging from our inductive research methods.  Trump Trolls Love to Post a ..read more
Visit website
Tulsi Gabbard and MAGA on Twitter
DiscoverText | Machine-learning on text and Twitter data
by Stuart Shulman
4y ago
Having spent the last two weeks documenting the extensive role of MAGA-related Twitter accounts in the Canadian election, let’s turn back to the United States and check in with the Democratic party primary where a food fight recently broke out. Tulsi2020 Candidate Tulsi Gabbard is getting a much closer look these days. The assertion by HRC that she is a product of Russian grooming definitely got a lot of press, but most of it was opinion-based (bashing Clinton, see Van Jones on CNN for example) rather than a data-based analysis of the role that foreign actors have played promoting the Gabbard ..read more
Visit website
Oh Canada: Before You Vote…
DiscoverText | Machine-learning on text and Twitter data
by Stuart Shulman
4y ago
First, let’s celebrate that Canadians vote today and the right to vote is a hard earned and cherished freedom worth defending. At the polls today will be generations of descendants of Canadians who fought for: democracy against the onslaught of authoritarianism, justice in the face of oppression, peace in the crucible of war, and  love in the face of hatred, bigotry, and other resentments. As a proud Canadian citizen, I wrote nine blog posts over a period of two weeks to alert readers, journalists, and voters to the creep of all those historical trends in Twitter networks (primarily the ..read more
Visit website
Bots, Trolls and Elections: Part Eight
DiscoverText | Machine-learning on text and Twitter data
by Stuart Shulman
4y ago
[You can start this series of posts by reading Part One and Part Two.] Today we return to “TrudeauMustGo” as well as the three other candidate collections. We seek to update readers on the status of the election interference built on circulating this rhyming trope as well as the preponderance of purported MAGA accounts active in the Canadian election. As of October 15, we had collected ~525,000 Tweets using the Twitter Search API and the search string TrudeauMustGo. These data include mentions of the phrase in the original text (roughly 50% of the data), but also in the retweets, replies, and ..read more
Visit website
Bots, Trolls and Elections: Part Six
DiscoverText | Machine-learning on text and Twitter data
by Stuart Shulman
4y ago
In Part Five of the series, we admitted that when studying a social virus, it is “difficult to place content (text, images, videos, news, identities) spreading on Twitter accurately into categories that are tied to the account history, such as human-vs-machine, manual-vs-automatic, real-vs-fake.” Difficult does not mean impossible and some errors along the way do not invalidate the research journey. So on we go. Now in Part Six, we explore the largest 1-day spike of the most active day since we began collecting data for this investigation on September 7, 2019. In Part Seven, we introduce the m ..read more
Visit website
Bots, Trolls and Elections: Part Five
DiscoverText | Machine-learning on text and Twitter data
by Stuart Shulman
4y ago
In Part Four of this series, we argued “Twitter inadvertently engineered a platform for A/B testing ideological warfare. In truth, it is A/B/C/D/E testing on toward infinity.” In the simplest colloquial terms: Russian agents can test politically disruptive messages to see what works best. Twitter makes it easy and inexpensive to introduce a social virus. This is not the type of virus that requires (currently) special anti-virus software to protect your computer. A social virus is an idea. Increasingly it is a virulent meme. Sometimes it is a trope. It can often be linked to a variety of mechan ..read more
Visit website

Follow DiscoverText | Machine-learning on text and Twitter data on FeedSpot

Continue with Google
Continue with Apple
OR