Thursday, November 13, 2008

Post 11/13/2008

  • How does it work?
    For a long period of time, we have been training our system to recognize texts that characterize the different types. The system, typealyzer, can now by itself find features that distinguishes one type from another. When all features, words and sentences, are combined typealyzer is able to guess which type its is most likely to be written by using statistical analysis.

    How can a computer know who I am?
    It doesn´t. But with a good amount of text it can make a pretty good guess. In addition, we all have different roles in different situations. By studying how people write, we can get an glimpse of what is on the mind of the person and what is characteristic of the person - or, as in the case of a blog - what is typical of the role/persona used when writing that blog. A person can have several blogs - and often have different roles for the various blogs - perhaps as a way to live out more sides of themselves.

    What’s the technology you use?
    Probability theory, statistics and a naive bayesian classifier.

    My blog is a ISTP - The Mechanics
    [ISTP]
    The independent and problem-solving type. They are especially attuned to the demands of the moment are masters of responding to challenges that arise spontaneously. They generelly prefer to think things out for themselves and often avoid inter-personal conflicts.

    tags: blogging, textanalysis, typealyzer


Posted from Diigo. The rest of my favorite links are here.

0 comments: