Using AOP neural networks to infer user behaviours and interests

Generally, users of an 'ego' social network provide personal information and actively participate in groups to discuss some topic. We propose a multi-agent driven system to analyse user behaviour and interests by gathering data related to different activities and show that a more comprehensive identity can be built from sparse data, while possibly reveal the tentative of some users to deceive other people. In our approach, user profiles are given to a profiling agent that retains relevant data by using ANN technologies that find categories for users. Even new users, whose profile is still mostly undefined, are given a 'most-likely' category, therefore the traits of such a category are inferred for new users. Since a group in a social network such as Facebook can be seen as a category, the agent driven system is also able to classify user profiles and recommend new groups users can subscribe to, according to their interests and preferences.