The TWIN Recommender System

From the 3rd International Workshop on Search and Mining User-generated Contents (SMUC 2011) there is an interesting paper

"A Comparative Evaluation of Personality Estimation Algorithms for the TWIN Recommender System"

".. the TWIN (Tell me What I Need) Personality-based Recommender System that analyzes the textual content of the reviews and estimates the personality of the user according to the Big Five model to suggest the reviews written by “twin-minded” people."
"We make an assumption that people having similar personality types would prefer to choose the same hotels as their twin-minded peer travellers. As significant correlations were found between words that people use and specific personality characteristics of the authors (here we consider the Big Five personality model) there is a possibility of creating a personality based user profile that estimates personality traits of the particular individual from the text written by him."
"In this paper we compare the performance of 4 algorithms for estimating the author's personality from the text, using a dataset of user-generated reviews crawled from the TripAdvisor"

WEAK POINTS:
* the authors estimate personality of users analyzing written text from users using M5’ regression tree algorithm (It has DISTORTION)
"the occurrence of the particular words in the particular text reflects the personality of the author."
* the formula applied to calculate similarity, K-Means algorithm
* in some cases, it is value similarity and not personality similarity the key to create bonds, like
Value similarity is the missing link in explaining the musical bonding phenomenon [and not personality similarity], which seems to hold for Western and non-Western samples and in experimental and natural settings. (punch to Behavioural Recommenders.)

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

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.