AbstractIn this paper we introduce an approach for achieving a self that is able to simulate average ethical intuitions by retrieving knowledge about human behavior from the Internet resources. We show how applying text mining techniques could be useful for virtual and physical agents which base their knowledge on natural language. We discuss the importance of empathy and pros and cons of crowd experience based algorithm, then we introduce our thoughts on possibility of manufacturing agents for particular purposes as behavior analyzers or moral advisors which could refer to millions of different experiences had by people in various cultures. We think such systems could lead to selves that are capable to non-biased decisions morally superior to these of average human.
Tech. Reports from AAAI Spring Symposium on Implementing Selves with Safe Motivational Systems & Self-Improvement: 40-44