1 / 17

30,000,000 Occupation Tweets A hashtag co-occurrence network analysis of information flows

Preliminary “Findings”. 30,000,000 Occupation Tweets A hashtag co-occurrence network analysis of information flows. Jeff Hemsley , Katherine Thornton, Josef Eckert, Shawn Walker, Robert M. Mason & Karine Nahon. NSF Award #1243170

gauri
Télécharger la présentation

30,000,000 Occupation Tweets A hashtag co-occurrence network analysis of information flows

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. Preliminary “Findings” 30,000,000 Occupation TweetsA hashtag co-occurrence network analysisof information flows Jeff Hemsley, Katherine Thornton, Josef Eckert, Shawn Walker, Robert M. Mason & KarineNahon

  2. NSF Award #1243170 INSPIRE: Tools, Models, and Innovation Platforms for Research on Social Media

  3. #Overview Occupy & Question Literature & Data Model & Findings Next Steps?

  4. #Occupy 9/17 to 10/15 • 21K+ Occupiers • 2300+ cities Meetup.com

  5. #Occupy Tweets: 300K to 1M a day 30,000,000 by end of 2011

  6. #Question Are there hashtag co-occurrence patterns indicative of organizing, informing and community building in the Occupy Twitter stream from October 19th to November 5th?

  7. #Literature Organizing Informing Community • Tagging as finding and filtering mechanism • Huang, J., Thornton, K.M., and Efthimiadis, E.N. Conversational tagging in twitter. Proceedings of the 21st ACM conference on Hypertext and hypermedia, ACM (2010), 173–178. • Mechanism of organizing information • Chang, H.C. A new perspective on Twitter hashtag use: Diffusion of innovation theory. Proceedings of the American Society for Information Science and Technology 47, 1 (2010), 1–4. • Information sharing • Java, A., Song, X., Finin, T., and Tseng, B. Why we twitter: understanding microblogging usage and communities. Proceedings of the 9thWebKDD and 1st SNA-KDD 2007 workshop on Web mining and social network analysis, ACM (2007), 56–65 • Particularly about events • Letierce, J., Passant, A., Breslin, J., and Decker, S. Understanding how Twitter is used to spread scientific messages. (2010). • Injecting messages into an information topic stream • Huang, J., Thornton, K.M., and Efthimiadis, E.N. Conversational tagging in twitter. Proceedings of the 21st ACM conference on Hypertext and hypermedia, ACM (2010), 173–178. • Letierce, J., Passant, A., Breslin, J., and Decker, S. Understanding how Twitter is used to spread scientific messages. (2010). • Community building mechanism • Laniado, D. and Mika, P. Making sense of twitter. The Semantic Web–ISWC 2010, (2010), 470–485. • Connect with like-minded individuals • Java, A., Song, X., Finin, T., and Tseng, B. Why we twitter: understanding microblogging usage and communities. Proceedings of the 9th WebKDD and 1st SNA-KDD 2007 workshop on Web mining and social network analysis, ACM (2007), 56–65. • Discussion participation & network enhancing • Letierce, J., Passant, A., Breslin, J., and Decker, S. Understanding how Twitter is used to spread scientific messages. (2010).

  8. #Literature • 140-character limit => expect limited or no meta-data • Huang, J., Thornton, K.M., and Efthimiadis, E.N. Conversational tagging in twitter. Proceedings of the 21st ACM conference on Hypertext and hypermedia, ACM (2010), 173–178. • Occupy tweets with multiple hashtags? • “Tweak the Tweet”: hashtags as metadata • Starbird, K., and J. Stamberger. 2010. “Tweak the Tweet: Leveraging Microblogging Proliferation with a Prescriptive Syntax to Support Citizen Reporting.” • Target interest sub-sets with multiple tags

  9. #Occupy #Tweets account1: support from #occupySydney#solidarity @OccupyChicago: The twentysix women in this policewagon say hello! #occupychicago#occupyarrests account2: RT@OccupyDenver Snow expected for #OccupyDenvertonight, 4-8 inches. Donations of warm clothing, etc would rock! #needsoftheoccupiers #ows account3: #GeneralStriketo give everyone a chance to #MoveYourMoneyon #Nov5 account4: What happened to #OccupyOaklandand the MSM response to it is further proof we need to #OccupyTheMediawith our own Internet media outlet.

  10. #Expectations • Hashtags as meta information for organizing information • Informing • Location & Events • Location & Utility • Community • Location &Location • Location & Slogan • Meta meta • Meta & Location • Meta & Slogan

  11. #Expectations

  12. #Data Y: Co-occurrence Matrix X1…Xn: tag by tag dummy • SoMeLab data set: 30,000,000 Occupy Tweets • Tweets with 2 or more tags • Oct 20 – Nov 5, 2011

  13. #Analysis Y: Co-occurrence Matrix X1…Xn: tag by tag dummy • Network Linear Regression • Quadratic Assignment Procedure • Proportion random trials • Test for association • T-test

  14. #Findings

  15. #Findings #Issues • Meta: OWS is a hub and tied to everything • Volume of OWS: signaling community • Not so distributed? • OWS Power Law: other news-like social attention? • Fire-bomb / noise / message injection

  16. #Future #Directions 3D Matrix -> meta & location & utility Location: control for distance Block Model #GetAJob

  17. So Me Lab S ocial Media Lab @ UW http:// so melab.net Thank you jhemsley@uw.edu

More Related