Welcome to EverybodyWiki ! Nuvola apps kgpg.png Sign in or create an account to improve, watchlist or create an article like a company page or a bio (yours ?)...

Texifter

From EverybodyWiki Bios & Wiki
Jump to navigation Jump to search






Texifter, LLC
Texifter LLC Logo 20180123.png
DiscoverText Screenshot 20180123.png
The DiscoverText Dashboard
Type of businessPrivate
Type of site
Social media analytics, Social networking service, Data mining
FoundedAmherst, MA, United States (2009)
Headquarters237 Shutesbury Rd. Amherst MA 01002
United States[1]
Area servedWorldwide
Founder(s)Dr. Stuart W. Shulman (CEO)[2]
Key peopleDr. Stuart W. Shulman (CEO)
Mark J. Hoy (CTO)
James Elgart (CFO)
IndustryInternet
Employees1-10
Websitehttps://texifter.com/
RegistrationFree Trial, Professional, Enterprise
Users<1000 (2018)
LaunchedNovember 2009; 10 years ago (2009-11)
Current statusActive

Overview[edit | edit source]

Texifter, LLC is a company offering the web-based products DiscoverText, a software tool for textual data collection and analysis and an additional tool, Sifter, which provides access to the Gnip historical archive of Twitter tweets.[3][4]

History[edit | edit source]

Texifter, LLC is a spin-out company based on text mining research conducted by Dr. Stuart Shulman.[5] Dr. Shulman previously worked primarily in the domain of U.S. federal government electronic rulemaking, with a specific focus on the development of human language tools for reviewing large numbers of public comments about proposed regulations.[6][7]

Software and services[edit | edit source]

DiscoverText[edit | edit source]

DiscoverText provides cloud-based text analytics software tools to analyze and evaluate large amounts of data, including unstructured text, survey results, blog posts, and social media messages.[8] It then uses machine learning classifiers to recognize text and social media data that the user considers relevant.

Using Gnip PowerTrack for Twitter, DiscoverText provides access to the full Twitter firehose for analysis and research.[9] Rules can be created to narrow search results to tweets containing (or lacking) specific search criteria, such as language, geographic location (geocoding), and the user’s bio information such as their URL and number of followers.[10]

Multilingual data can be imported from various sources or APIs, including Twitter, SurveyMonkey, RSS, spreadsheets, XML files, and text files.[3][10]

Sifter[edit | edit source]

A companion product, Sifter, performs a similar function, but can search for and retrieve any undeleted tweet since the beginning of Twitter.[11]

Use in research studies[edit | edit source]

DiscoverText has been used by researchers for several social media measurement studies, including analyzing the sentiments of Twitter messages to evaluate public opinion regarding the performance of the Brazilian government and the effectiveness of tweets about HIV prevention.[12][13] In 2012, the National Library of Norway evaluated DiscoverText as a means to preserve Twitter posts for posterity.[10]

Patent and federal supply schedule[edit | edit source]

On March 1, 2016, Texifter, LLC was granted a US patent for its “systems and methods… for machine classifiers that employ enhanced machine learning.”[14]

DiscoverText and Sifter are on the US General Services Administration (GSA) federal supply schedule.[15]

Competition[edit | edit source]

With the rise of social media, many researchers, government officials, and company marketing departments look for tools available from multiple vendors to automate their data mining and sentiment analysis efforts.[16][17] As a result, Texifter participates in a marketplace with several text mining software tools.

See also[edit | edit source]

Further reading[edit | edit source]

References[edit | edit source]

  1. "Texifter Contact Us". Texifter. Retrieved January 23, 2018.
  2. "Texifter Crunchbase Profile". "Crunchbase". Retrieved January 23, 2018.
  3. 3.0 3.1 Shulman, S. (2011-06-12). "DiscoverText: software training to unlock the power of text". Proceedings of the 12th Annual International Digital Government Research Conference: Digital Government Innovation in Challenging Times: 373–373. doi:10.1145/2037556.2037632. ISBN 978-1-4503-0762-8 – via ACM.
  4. Driscoll, K.; Walker, S. (2014). "Working Within a Black Box: Transparency in the Collection and Production of Big Twitter Data". International Journal of Communications. 8: 1745–1764.
  5. "Texifter at Crunchbase". crunchbase. Retrieved January 25, 2018.
  6. "DiscoverText About Us". DiscoverText. 2018. Retrieved January 25, 2018.
  7. Shulman, Stuart (2009). "The Case Against Mass E-mails: Perverse Incentives and Low Quality Public Participation in U.S. Federal Rulemaking" (PDF). University of Washington Faculty Website. Retrieved February 9, 2018.
  8. "Bloomberg Company Overview of Texifter, LLC". Bloomberg. Retrieved January 25, 2018.
  9. Chung, J. E. (April 2017). "Retweeting in health promotion: Analysis of tweets about Breast Cancer Awareness Month". Computers in Human Behavior. 74: 112–119. doi:10.1016/j.chb.2017.04.025.
  10. 10.0 10.1 10.2 Beyer, Y. (December 2012). "Using DiscoverText for Large Scale Twitter Harvesting" (PDF). Microform & Digitization Review (3–4): 121–125. doi:10.1515/mir-2012-0019. ISSN 2190-541X.
  11. "Historical twitter data using sifter". Texifter.com. Retrieved January 25, 2018.
  12. Oliveira, D.J.S.; Bermeno, P.H.S. (July–September 2017). "Mídias sociais e administração pública: análise do sentimento social perante a atuação do Governo Federal brasileiro" [Social media and public administration: social sentiment analysis about the performance of the Brazilian Federal Government]. Organizações & Sociedade. 24. doi:10.1590/1984-9240827. ISSN 1984-9230.CS1 maint: Date format (link)
  13. McLaughlin, Margaret L.; Hou, Jinghui; Meng, Jingbo; Hu, Chih-Wei; An, Zheng; Park, Mina; Nam, Yujung (April 29, 2015). "Propagation of Information About Pre-Exposure Prophylaxis (PrEP) for HIV Prevention Through Twitter". Health Communication. SSRN 2605632.
  14. Shulman, Stuart (March 1, 2016). "System and method of classifier ranking for incorporation into enhanced machine learning US 9275291 B2". Google Patents. Retrieved January 25, 2018.
  15. "GENERAL SERVICES ADMINISTRATION FEDERAL SUPPLY SERVICE AUTHORIZED FEDERAL SUPPLY SCHEDULE PRICE LIST" (PDF). GSA Advantage. Retrieved January 25, 2018.
  16. Medri, Daniele (October 21, 2013). "Big Data & Business: An on-going revolution". Statistics Views. Retrieved January 25, 2018.
  17. Shaffer, Elizabeth M.; Freund, Luanne; Welch, Mackenzie (May 2013). "Tweeting the Government: Preliminary findings from a genre analysis of Canadian federal government tweets". bepress. Retrieved January 25, 2018.

External links[edit | edit source]

Category:Companies based in Massachusetts Category:Data differencing Category:Data miners Category:Data mining Category:Data_mining_and_machine_learning_software Category:Internet properties established in 2009 Category:Machine learning Category:Natural language processing Category:Twitter services and applications PSRI JP (talk) 23:15, 27 January 2018 (UTC)


This article "Texifter" is from Wikipedia. The list of its authors can be seen in its historical and/or the page Edithistory:Texifter. Articles copied from Draft Namespace on Wikipedia could be seen on the Draft Namespace of Wikipedia and not main one.



Compte Twitter EverybodyWiki Follow us on https://twitter.com/EverybodyWiki !