User Tag List

First 12

Results 11 to 19 of 19

  1. #11
    Member chaoticbrain's Avatar
    Join Date
    Jul 2013
    MBTI
    NeTi
    Enneagram
    6 sx
    Posts
    82

    Default

    Double post

  2. #12
    Senior Member
    Join Date
    Aug 2013
    MBTI
    ISTP
    Posts
    353

    Default

    Quote Originally Posted by chaoticbrain View Post
    Woah, that's a lot of data.

    And ya I can still help you if you want me to try collecting data, but I'm not even sure how you collected that much.

    Out of curiosity, do you need programming knowledge to run something like this ?
    In order to collect this data I spidered the first page of half the threads on the forum. You definitely need programming knowledge to do that.

    I really need a much bigger dataset. And a big part of the problem is that I need the author to be accurately typed.. at least on average, but preferably all the time.

  3. #13
    Wake, See, Sing, Dance Cellmold's Avatar
    Join Date
    Mar 2012
    Posts
    5,806

    Default

    Quote Originally Posted by funtensity View Post
    I really need a much bigger dataset. And a big part of the problem is that I need the author to be accurately typed.. at least on average, but preferably all the time.
    Well once you've cracked that you have cracked most of typology.
    'One of (Lucas) Cranach's masterpieces, discussed by (Joseph) Koerner, is in it's self-referentiality the perfect expression of left-hemisphere emptiness and a precursor of post-modernism. There is no longer anything to point to beyond, nothing Other, so it points pointlessly to itself.' - Iain McGilChrist

    Suppose a tree fell down, Pooh, when we were underneath it?"
    "Suppose it didn't," said Pooh, after careful thought.
    Piglet was comforted by this.
    - A.A. Milne.

  4. #14
    garbage
    Guest

    Default

    Damn, man. Actual empirical testing. Gotta love it.

    How does your method fare on dichotomies rather than functions? Might be worth trying out.

  5. #15
    this is my winter song EJCC's Avatar
    Join Date
    Aug 2008
    MBTI
    ESTJ
    Enneagram
    173 so/sx
    Posts
    18,432

    Default

    Looking good so far! Interested in how this will end up going.

    Might be worth going to another forum or two to add supplemental data for the types on the lower end of the posting spectrum? e.g. the SJ posts are primarily going to be a handful of people (me, giggly, puremercury, Patches, etc), which isn't a diverse set of styles to go from.
    ~ g e t f e s t i v e ! ~


    EJCC: "The Big Questions in my life right now: 1) What am I willing to live with? 2) What do I have to live with? 3) What can I change for the better?"
    Coriolis: "Is that the ESTJ Serenity Prayer?"



    ESTJ - LSE - ESTj (mbti/socionics)
    1w2/7w6/3w4 so/sx (enneagram)
    want to ask me something? go for it!

  6. #16
    Senior Member
    Join Date
    Jan 2013
    Posts
    795

    Default

    personalitycafe would be a good one. They have a nice mix of types there, and more feelers.

  7. #17
    failure to thrive AphroditeGoneAwry's Avatar
    Join Date
    Feb 2009
    MBTI
    INfj
    Enneagram
    451 sx/so
    Socionics
    ENFj Ni
    Posts
    5,651

    Default

    I'm accurately typed.

    Cool beans. At one point, I also wanted to come up with better cognitive functions tests.
    Ni/Ti/Fe/Si
    4w5 5w4 1w9
    ~Torah observant, Christ inspired~
    Life Path 11

    The more one loves God, the more it is that having nothing in the world means everything, and the less one loves God, the more it is that having everything in the world means nothing.

    Do not resist an evil person, but to him who strikes you on the one cheek, offer also the other. ~Matthew 5:39

    songofmary.wordpress.com


  8. #18
    Senior Member
    Join Date
    Aug 2013
    MBTI
    ISTP
    Posts
    353

    Default

    Quote Originally Posted by bologna View Post
    Damn, man. Actual empirical testing. Gotta love it.

    How does your method fare on dichotomies rather than functions? Might be worth trying out.
    I have not yet tested functions - the above results are all on trying to classify entire types.

    I ran some experiments on trying to classify dichotomies. Here are the results:

    Code:
    IE mean = 63.08%, std_dev = 8.57%,  {75, 62, 56.25, 56.25, 56.25, 68.75, 50, 75, 62.5, 68.75}
    SN mean = 81.25%, std_dev = 10.21%, {87.5, 68.75, 87.5, 75, 87.5, 68.75, 100, 75, 75, 87.5}
    TF mean = 63.75%, std_dev = 10.94%, {50, 68.75, 68.75, 62.5, 62.5, 81.25, 50, 50, 68.75, 75}
    JP mean = 66.67%, std_dev = 10.21%, {68.75, 56.25, 81.25, 56.25, 62.5, 75, 62.5, 62.5, 56.25, 62.5}

    The dataset consists of 1067 randomly chosen posts for each type since that is the number of posts for ESTJ, which is the type that has posted the least here. This means I threw out the vast majority of the data. I then cut off each type at 61693 words, since that is the number of words that ENFPs, who use the fewest words per post, used in 1067 posts. I then did 10-fold cross validation (randomly selected 90% of the data for training, and 10% for testing 10 times) and averaged the results.

    As you can see, the results are above 50%, which is the result that a classifier that always guessed 'E' (for example) would get.

    However, there are still problems with the data. The training and testing sets contain posts from the same members. And all of the posts are from this website.

    I'm thinking about spidering OkCupid for a dataset.

  9. #19
    Senior Member
    Join Date
    Aug 2013
    MBTI
    ISTP
    Posts
    353

    Default

    I am sad to say that I can't afford to keep working on this project.

    However, if someone else can manage to collect a large quantity of text for each type, I would be more than happy to run my analyses on it, and even document how to do the analysis. I strongly believe that in the limit of data (gobs and gobs of sweet, sweet data) this idea can work.

Similar Threads

  1. [JCF] For those who are new to the cognitive function theory
    By wolfnara in forum Myers-Briggs and Jungian Cognitive Functions
    Replies: 6
    Last Post: 03-25-2016, 10:34 PM
  2. Cognitive functions in use test?
    By Jacobman77 in forum Myers-Briggs and Jungian Cognitive Functions
    Replies: 0
    Last Post: 04-04-2015, 10:20 AM
  3. [ENFP] ENFPs cognitive functions test results :)
    By mackie in forum The NF Idyllic (ENFP, INFP, ENFJ, INFJ)
    Replies: 104
    Last Post: 09-01-2010, 01:59 PM
  4. [JCF] Leanor Thomson's Theory and INFP cognitive functions
    By heart in forum The NF Idyllic (ENFP, INFP, ENFJ, INFJ)
    Replies: 1
    Last Post: 08-31-2007, 01:07 AM
  5. Cognitive Functions Test?
    By MerkW in forum Online Personality Tests
    Replies: 3
    Last Post: 08-23-2007, 04:01 PM

Posting Permissions

  • You may not post new threads
  • You may not post replies
  • You may not post attachments
  • You may not edit your posts
Single Sign On provided by vBSSO