TED Community » Sebastian Wernicke

More About Me

I'm passionate about

wit, food, statistics, flightless birds, and all other things fascinating

People don't know that I'm good at

...sleeping. Already missed two earthquakes.

Comments

• TEDCred score: +138.30 TEDCred reflects your contribution to the TED community.

• +8

  A reply on Talk: Sebastian Wernicke: 1000 TEDTalks, 6 words

  Jan 10 2012: The 6 words that occur most in TED Talks are actually not that interesting. They are "the", "and", "to", "of", "a", and "that", all among the Top-10 of the most common words in the English language. Together they make up 18% of all words in the first 970 TED Talks.
  With nouns, it becomes more interesting, then you get "people", "world", "time", "human", "idea", and "fact".
  If you want to go even deeper - i.e., into statistical significance - then you might want to take a look at http://blog.ted.com/2011/06/27/new-stats-sebastian-wernickes-tedtalk-analysis-updated/
• +4

  A reply on Talk: Sebastian Wernicke: 1000 TEDTalks, 6 words

  Jan 9 2012: Certainly the TED community can provide great six-word summaries of TED Talks (and many have). But for this "experiment" there were two requirements that would otherwise have been hard to fulfill:
  1) The summaries needed to exhaustively and uniformly cover all talks in a restricted period of time.
  2) For the "summaries of the summaries", it was important to me that the result would really be something coming out of the process, e.g., I wanted "objective" summaries of all the persuasive talk summaries instead of people expressing in six words what they find persuasive about TED (which is of course also a very interesting thing to ponder).
• +1

  A reply on Talk: Sebastian Wernicke: 1000 TEDTalks, 6 words

  Jan 7 2012: Not an intentional omission. The book "Not Quite What I Was Planning: Six-Word Memoirs by Writers Famous and Obscure" (by Rachel Fershleiser and Larry Smith) actually gave me the idea for this talk. The "six word memoir" website from Smith magazine (http://www.smithmag.net/sixwords/) is also quite addictive.
• +7

  A reply on Talk: Lies, damned lies and statistics (about TEDTalks)

  May 2 2010: Most parts of data gathering and analysis were a combination of Linux scripts and a (large) spreadsheet. However, two parts of the text analysis required special linguistic analysis software:
  1) The top-10 word list (you need the tool to "normalize" words so that, e.g., different verb forms will be counted as the same word).
  2) The most-favorite and least-favorite topics. This is based on a so-called "semantic analysis", where words are automatically grouped into a (manually curated) topic structure.
  
  Text analysis in relations to stock price movements is in fact already being done by several financial institutions, with computers automatically interpreting and trading on news they receive via agency tickers (e.g., see http://en.wikipedia.org/wiki/Algorithmic_trading#Issues_and_developments).
• +3

  A reply on Talk: Lies, damned lies and statistics (about TEDTalks)

  May 1 2010: I can fully second that, the crowd at this year's TEDActive was the best audience I (or any other speaker) could ever have wished for. There was a lot of energy in the room and it felt easy to connect with the everyone because the atmosphere was extremely receptive and responsive.
• +1

  A reply on Talk: Lies, damned lies and statistics (about TEDTalks)

  May 1 2010: A suitable tool for executing madness is often a huge spreadsheet (ask anyone working in Finance). Downloading the transcripts, ratings and videos was done with a bunch of open source tools.
• +6

  A reply on Talk: Lies, damned lies and statistics (about TEDTalks)

  May 1 2010: Never trust statistics - ever! However, I think there are at least three parts in the analysis where causation is actually plausible (then again, maybe I have spent too much time with the subject matter and start to see patterns everywhere):
  1. The picture shown at 1:11 in the video is an actual correlation mapping between audience ratings. I think it makes sense that the general direction of the topic (rational vs. emotional, actions vs. ideas) should spark specific audience reactions.
  2. The picture shown ar 1:56 is derived from a semantic analysis (where words are automatically grouped into topics by a software tool). I think it makes sense that there is a tendency to rate those talks as your favorite that you can seasily connect with emotionally.
  3. Regarding the four word phrases at 3:03, it seems to me that those appearing in the most favorited TED talks are much more audience-centric than those in the least favorited TED talks.

• A reply on Talk: Lies, damned lies and statistics (about TEDTalks)

  May 1 2010: Funny you should mention the color of my pants and the glasses. While both of these choices were not deliberate, you actually do start thinking about these things when you spend too much time with the data.