Skip to content
62 | Text Visualization: Past, Present and Future with Chris Collins episode artwork

Oct 29, 2015 1 hr 5 min

62 | Text Visualization: Past, Present and Future with Chris Collins

from Data Stories Hosted by Enrico Bertini and Moritz Stefaner

We have Assistant Professor Chris Collins from University of Ontario Institute of Technology on the show to talk about text visualization. Chris explains what Text Vis is, provides examples from his and others' work, describes tools and knowledge to get started, and looks into the future of the field, including its challenges and opportunities. And here's a really cool new thing — we have a transcript of the whole show! Browse the text, search for quotes and chapters, and maybe even… visualize it? Let us know if it's useful! Enjoy the show! LINKS Chris Collins and His Lab FluxFlow (twitter rumors detection and visualization) | See also “How riot rumours spread on Twitter” (from the Guardian) Probing Projections Project DocuBurst Patterns in Passwords Book: “Graphs, Maps, and Trees” Lexichrome (visualizing the color of words) Literature Fingerprinting (showing how different authors write) (PDF) Visualizing Text Readability (PDF) Text visualization browser (collection/taxonomy of text vis projects) [good place to start looking into text vis!] NLTK (Natural Language Toolkit) Wordnet This episode is sponsored by Qlik who allows you to explore hidden relationships within data that lead to insights. Check out the virtual event on Nov 18: Are you seeing the whole story that lives within your data? You can download Qlik Sense for free at: www.qlik.de/datastories.

Episode details come from the podcast's RSS feed.

Embed this episode

Ready to play

62 | Text Visualization: Past, Present and Future with Chris Collins

0:00 1:05:23

Chapters

  1. 0:05 Our sponsor: Qlik
  2. 0:41 Mo and Enrico catch up
  3. 1:46 Our guest: Chris Collins
  4. 3:05 ELIZA
  5. 4:42 What is text visualization?
  6. 10:55 Flux Flow
  7. 17:17 Probing projections
  8. 20:50 DocuBurst
  9. 26:24 Patterns in passwords
  10. 31:39 Correct Horse Battery Staple
  11. 34:06 Our sponsor: Qlik
  12. 35:46 Lexichrome
  13. 40:40 Literature Fingerprinting
  14. 41:31 Readability work
  15. 41:44 How to get started?
  16. 42:07 Text visualization browser
  17. 42:58 NLTK (Natural Language Toolkit)
  18. 43:09 Wordnet
  19. 46:35 How to process texts
  20. 51:00 What are the challenges?
  21. 55:46 TAPoR
  22. 58:17 Future directions
  23. 1:04:54 Our sponsor: Qlik

No transcript yet.

Requests help us decide what to transcribe next.

Frequently asked questions

How long is this episode of Data Stories?

This episode is 1 hour and 5 minutes long.

When was this Data Stories episode published?

This episode was published on October 29, 2015.

Can I download this Data Stories episode?

Yes. Use the download control on the episode player to save the publisher-provided media file.