Sunday, April 8, 2012

paper: "AUTOMATED PERSONALITY CLASSIFICATION"






PAPER "AUTOMATED PERSONALITY CLASSIFICATION"
"Abstract – In this paper we give a description of the problem of the automated personality classification (APC) and the presentation of the existing solutions to
this problem. As a scientific contribution, we present a classification of the existing solutions to the problem of the APC. We also expose several ideas for development of new solutions to this problem and for improvement of the existing ones. Future directions for solving the problem of the APC in the context of social networks are also discussed."

"In [32] (paper 'Personality based latent friendship mining')  proposed a method that solves the problem finding compatible friends among bloggers (Figure 3). Unlike previous approaches to solving this problem where it was assumed that compatible bloggers write about related subjects, the authors here using the hypothesis that bloggers are compatible with similar personality characteristics."

"4) IDEAS FOR FUTURE WORK
In this section we present some ideas for improving AKL.
For clarity, the ideas are categorized as follows way: A) new types of Corps B) new ways of measuring personality traits, C) a new method for classifying and D) Dynamic AKL (automated classification of personality)."
(You can use Google to translate from Serbian to English)

------------------------------------------------------------

Personality Based Recommender Systems are the next generation of recommender systems because they perform FAR better than Behavioural ones (past actions and pattern of personal preferences)
That is the only way to improve recommender systems, to include the personality traits of their users.
Have you seen they need to calculate personality similarity between users?
Have you seen there are different formulas to calculate similarity?
In case you did not notice, recommender systems are morphing to .......... compatibility matching engines!!!
They mostly use the Big5 to assess personality and the Pearson correlation coefficient to calculate similarity.

LIFEPROJECT METHOD is also suitable for personality based recommender systems because it uses the 16PF5 normative personality test, available in different languages to assess personality of members, or a proprietary test with exactly the same traits of the 16PF5. The ensemble of the 16PF5 is: 10E16, big number as All World Population is nearly 7.0 * 10E9 (estimated OCT 2011)
and
calculates similarity between persons with a quantized pattern comparison method (part of pattern recognition by cross-correlation). It takes into account the score and the trend to score of any pattern.

LIFEPROJECT METHOD is like the Teller Ulam design for recommender systems and the Online Dating Industry.

No comments:

Post a Comment