Highlights from #cj2014 opening keynote: Jon Kleinberg

I’m following the Computation + Journalism 2014 symposium via the hashtag and livestream. Below are some highlights I collected from the opening keynote.

#cj2014: Tracing the Flow of On-Line Information through Networks and Text

Keynote by Jon Kleinberg at 2014 Computation + Journalism symposium at Columbia University

  1. Event page:
  2. Highlights from the keynote (in chronological order):
  3. Keynote by Jon Kleinberg of Cornell: metaphors of information travelling online include the library and the crowd #cj2014
  4. #Information travels on-line via #library (pages, links, association) & crowd (memes, contagion) | #data #CJ2014
  5. Jon Kleinberg opens #CJ2014 with a ref to the classic essay As We May Think.  http://j.mp/ZPWaO1 
  6. Jon Kleinberg, speaking right now at #cj2014, did some really cool work tracking chain letters online in 2008  http://www.pnas.org/content/105/12/4633.full 
  7. We can track the flow of information temporally, structurally, and in terms of content, says Jon Kleinberg #cj2014
  8. But are crowd & library metaphors dual: people trailblazing through documents or documents transmitted through networks of people? #cj2014
  9. It’s easier for algorithms to track items (quotes, photos, phrases) than stories. Q: Does that encourage pack journalism? #CJ2014
  10. Tracking stories through networks reveals difficulties eg., natural language. But can track quotes to show news cycles #CJ2014
  11. Kleinberg explains tracking essential elements of a story (like phrases) as they move through networks. #cj2014 http://t.co/V1fiFZWUBS

    Kleinberg explains tracking essential elements of a story (like phrases) as they move through networks. #cj2014 pic.twitter.com/V1fiFZWUBS
  12. Half of all reshares on FB happen in large cascades (>500) | #paradox #viral #CJ2014
  13. Basic question: how to predict what content will be shared widely? Or, are cascades unpredictable? #cj2014 http://t.co/Q7dCleEkXH

    Basic question: how to predict what content will be shared widely? Or, are cascades unpredictable? #cj2014 pic.twitter.com/Q7dCleEkXH
  14. #cj2014 Is virality predictable? You as poster rarely experience it w your content, but you as consumer see it often http://t.co/IEgOmZtWIv

    #cj2014 Is virality predictable? You as poster rarely experience it w your content, but you as consumer see it often pic.twitter.com/IEgOmZtWIv
  15. One solution: reframe question as tracking rather than snapshot instant: what are the chances of this being shared further? #cj2014
  16. On whether something “goes viral”: “An important moment in a cascade is the moment it escapes the neighborhood of the root.” #cj2014
  17. Temporal features most powerful in predicting resharing of photo memes #CJ2014 http://t.co/3ZKFHIzO7Y

    Temporal features most powerful in predicting resharing of photo memes #CJ2014 pic.twitter.com/3ZKFHIzO7Y
  18. My thoughts are on how narratives or stories in news, eg images of ‘typical’ migrants, circulate and are widely diffused #cj2014
  19. Troubling finding here seems to be that actual content has less impact on how likely something is to go viral #cj2014 http://t.co/lver1zx14e

    Troubling finding here seems to be that actual content has less impact on how likely something is to go viral #cj2014 pic.twitter.com/lver1zx14e
  20. Research to understand discussion and comment threads - #cj2014 keynote by Jon Kleinberg http://t.co/3HUQi1uZj1

    Research to understand discussion and comment threads – #cj2014 keynote by Jon Kleinberg pic.twitter.com/3HUQi1uZj1
  21. Kleinberg now moving from global discussion to local conversations via threads or friends. What makes them engaging, long, short? #cj2014
  22. Tracking the virality of memes: Speed is important. Pics that get the first 1k of shares fast are more likely to go viral after. #cj2014
  23. Content more likely to spread if strangers share it = good reason for journalists to make sure their networks are diverse #CJ2014
  24. #visualization shows 2 kinds of threads: long due to many contributors posting once or convo among few ppl #cj2014 http://t.co/Js2wFv0lyy

    #visualization shows 2 kinds of threads: long due to many contributors posting once or convo among few ppl #cj2014 pic.twitter.com/Js2wFv0lyy
  25. Super interesting question!: why do certain quotes/content stand out? Linguistic markers? #visualization #cj2014 http://t.co/1muOY6tZxI

    Super interesting question!: why do certain quotes/content stand out? Linguistic markers? #visualization #cj2014 pic.twitter.com/1muOY6tZxI
  26. For a week in September 2008, Obama commandeered the news media with the line “lipstick on a pig,” says Jon Kleinberg #cj2014
  27. That would be a nice job description for a business card: Meme tracker. #cj2014
  28. Kleinberg compares memorable & unmemorable movie lines as lab setting to see what features contribute to memorable or viral text #CJ2014
  29. How to track virality of content - use movie quotes: "These aren't the droids you're looking for." #cj2014 http://t.co/Z1YqXGlsgM

    How to track virality of content – use movie quotes: “These aren’t the droids you’re looking for.” #cj2014 pic.twitter.com/Z1YqXGlsgM
  30. Why do we like “these aren’t the droids you’re looking for” but not “you don’t need to see his identification” #CJ2014
  31. Memorable quotes are sequences of unusual words with common part of speech patterns #cj2014 – application to headline writing?
  32. Memorable quotes are less probable in their word choices but more probably in their sentence (part-of-speech) structure – Kleinberg. #cj2014
  33. Jon Kleinberg: Socially shared information - how to predict success stories? Try a sequence of unusual words.#cj2014 http://t.co/AVzW3vImS6

    Jon Kleinberg: Socially shared information – how to predict success stories? Try a sequence of unusual words.#cj2014 pic.twitter.com/AVzW3vImS6
  34. Is there an algorithmic pattern to why a movie quote is memorable? Take “you had me at hello.” What’s so special about it? #cj2014
  35. “Memorable quotes need to have a certain portability” _Jon Kleinberg #cj2014
  36. Memorable quotes tend to be more ‘general’: more present tense, indefinite articles, fewer third-person pronouns >> ‘portability’ #cj2014
  37. #CJ2014 The ‘You had me at hello’ paper reference by Jon Kleinberg (including movie quotes memorability test):  http://www.mpi-sws.org/~cristian/memorability.html 
  38. Slogans in #advertising are like memorable quotes. “It just keeps going & going & going.” | #marketing #NLP #CJ2014
  39. Is there an analogy of genetics for text: ‘fitness’ of text for sharing, mutation of ‘junk’ parts of quotes while core parts remain #cj2014
  40. #cj2014 Just as genes have functional parts and junk parts, so does text - Beautiful analysis of content prolongation http://t.co/oFsLnMmrN7

    #cj2014 Just as genes have functional parts and junk parts, so does text – Beautiful analysis of content prolongation pic.twitter.com/oFsLnMmrN7
  41. “Genetic analogies for memes are becoming increasingly rich” -Jon Kleingberg #cj2014
  42. Sharing on social networks: “Can cascades be predicted?” — paper by Jon Kleinberg et al  http://bit.ly/1nCkspI  #cj2014
  43. Kleinberg wraps up his fascinating talk with new avenues for computational insight into info flows #CJ2014 http://t.co/vTloP7pllJ

    Kleinberg wraps up his fascinating talk with new avenues for computational insight into info flows #CJ2014 pic.twitter.com/vTloP7pllJ
  44. Great question: What are the features of content that make people STOP watching/reading/commenting? #CJ2014
  45. Another great question: Are there computational ways to evaluate WHO gets to be quoted in the first place? #CJ2014

Leave a Reply

Your email address will not be published. Required fields are marked *