Exploiting and Learning Human Temperaments for Customized Information Recommendation

C.-H. Lin and D. McLeod (USA)


Temperamentbased information filtering, concept learning, internet search technologies, user modeling, multiagent systems, human factors.


Human temperaments have been recognized as a predominant factor in determining the activity patterns of human behavior. In our earlier study, a temperament based filtering method has been proposed to combine concept learning and content-based filtering techniques to incorporate human temperament into the recommendation process of an information system. In this paper, we explain the design of a prototype multiagent system, which is developed, implemented, and experimentally tested by using a group of simulated users generated from the sample users. The notion of human factors, particularly human temperaments, is explored and learned for the representation and segmentation of an information space. Furthermore, the learned temperament concept is employed for the interpretation and measurement of the relevance for classification and recommendation of the information units. The results of our experiments indicate that the accuracy of recommendation using temperament based filtering exceeds that in content-based filtering. The quality of specific search as well as serendipitous search is enhanced by providing the optimal predictions that are pertinent to not only user interests but also user temperament.

Important Links:

Go Back