Are You Satisfied with Your Recommendation Service?: Discovering Social Networks for Personalized Mobile Services
Most of recommendation mechanisms have been attempting to identify a set of cohesive user groups (or clusters) of which members in the same group might be interested in a common area (e.g., movies and musics) than others. Practically, this assumption is not working well, because the statistical analysis to extract simple demographic features (e.g., ages, genders, and so on) can not find out personal context in a certain situation, i.e., a more specific recommendation for each person. In order to solve this problem, we want to take into account social relations (particularly, kin relations) to identify each person. As aggregating the social networks, we can build a social network for making various social relations extractable. Most importantly, we are introducing our experiences on discovering social networks for providing personalized mobile services. Real customer information has been provided from KT Freetel (KTF), one of the major telecommunication companies in Korea. This work is an on-going research project for delivering personalized information to mobile devices via the social networks.
KeywordsSocial Network Mobile User Personalized Service Calling Pattern Personal Context
Unable to display preview. Download preview PDF.
- 10.Jung, J.J.: Visualizing recommendation flow on social network. Journal of Universal Computer Science 11(11), 1780–1791 (2005)Google Scholar