Everyday a lot of subjects of interest (here called topics) are published on the Web and compete to reach an audience and to achieve their communicative goal. We propose an approach to these issues, based on two main propositions: First, each topic is personified by a conversational agent capable of interacting with users about the topic, Second, agent's reactions to users' requests involve traditional rational reactions but also relational reactions taking into account social roles.

In this paper, we present an approach based on the principle that psychological capacities, especially personality traits, influence the decision making process of rational agents. Using a three-level (trait, facet, scheme) extension of the FFM/NEO P

We describe here a framework dedicated to studies and experimentations upon the nature of the relationships between the rational reasoning process of an artificial agent and its psychological counterpart, namely its behavioral reasoning process. This study is focused on the domain of Assistant Conversational Agents which are software tools providing various kinds of assistance to people of the general public interacting with computer based applications or services. In this context, we show on some examples how the agents must exhibit both rational reasoning about the system functioning and a human-like believable dialogical interaction with the users.

We have defined a direct-execution model dedicated to non-numerical processing which is based upon an internal representation of source programs derived from LISP. This model provides good support for both sophisticated editing (syntactical parsing, tree manipulation, pretty-printing, ...) of conventional languages and artificial intelligence languages. A high level microprogramming language (LEM) was designed to write the interpreters and the editors. A hardware processor was built and a LISP interpreter, microprogrammed in LEM, has been operational since September 1980.

This paper describes the basic principles and the architecture of a general host machine based upon lists processing. Current works in this field are dealing with conventional direct execution schemes which use lineary structured Directly Executable Languages: prefixed languages with varying formats for operators and operands. If these languages are convenient for interpretation and provide an efficient execution scheme, on the other hand, they are very hard to generate.