I had been checking the list of accepted papers from RecSys 2011 Conference.
It seems some researchers in the recommendation systems arena had fallen asleep.
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.
RecSys 2010 Conference was full of papers about Personality based recommender systems, but this RecSys 2011 Conference has only one outstanding paper:
Rong Hu and Pearl Pu, 2011 "Enhancing Collaborative Filtering Systems with Personality Information"
"Collaborative filtering (CF), one of the most successful recommendation approaches, continues to attract interest in both academia and industry. However, one key issue limiting the success of collaborative filtering in certain application domains is the cold-start problem, a situation where historical data is too sparse (known as the sparsity problem), new users have not rated enough items (known as the new user problem), or both. In this paper, we aim at addressing the cold-start problem by incorporating human personality into the collaborative filtering framework. We propose three approaches: the first is a recommendation method based on users’ personality information alone; the second is based on a linear combination of both personality and rating information; and the third uses a cascade mechanism to leverage both resources.
To evaluate their effectiveness, we have conducted an experimental study comparing the proposed approaches with the traditional ratingbased CF in two cold-start scenarios: sparse data sets and new users. Our results show that the proposed CF variations, which consider personality characteristics, can significantly improve the performance of the traditional rating-based CF in terms of the evaluation metrics Mean Absolute Error (MAE) and Receiver Operating Characteristic (ROC) sensitivity."
A ROC sensitivity value of 1.0 indicates that the recommendation algorithm is able to predict all relevant items correctly, whereas a value of 0.0 indicates that it predicts any of the relevant items as bad.
Although there are some weak points like:
* Value similarity is the missing link in explaining the musical bonding phenomenon [and not personality similarity]
* personality measured by personality quizzes has HIGH DISTORTION. Big Five Factor personality model is an oversimplification.
* The personality similarity between two user "u" and "v" is computed using the Pearson correlation coefficient.
See how LIFEPROJECT METHOD calculates similarity.
Similarity in personality patterns with (a proprietary) pattern recognition by correlation method. It takes into account the score and the trend to score of any pattern.