The introduction of consumer broadband makes it possible to have an emotionally much richer experience of the internet. One way of achieving this is the use of animated characters endowed with emotionally expressive behaviour. This paper describes Demeanour, a framework for generating expressive behaviour, developed collaboratively by University College London and BT plc. The focus of this paper will be on two important aspects; the customisation of expressive behaviour and how expressive behaviour can be made context dependent.Customisation is a very popular feature for internet software, particularly as it allows users to present a specific identity to other users; the ability to customise beahviour will increase this sense of identity. Demeanour supports a number of user friendly methods for customisng behaviour, all of which use a character profile that ultimately controls the behaviour of the character.What counts as appropriate behaviour is highly dependent on the context, where you are, who you are talking to, whether you have a particular job or role. It is therefore very important that characters are able to exhibit different behaviours in different contexts. Demeanour allows characters to load different profiles in different contexts and therefore produce different behaviour.
Personal agents are an important advance in the management of electronic information. Accurate user profiling is critical to the personalisation of agent-based services. In this paper we describe a framework for personal agents, which provides a range of services using a common user profile. The user profile is automatically learned from observation of the electronic documents a user reads, and tracks user interests over time. We report on a large trial of this framework, which has given us important insights into the effectiveness of personal agent applications. In particular we discuss the benefits obtained from the use of a common profile and the interoperation of several personal agent applications.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.