Can proactive behavior turn chatterbots into conversational agents

Chatterbots are software systems interacting with their users by means of a natural language based conversation. Their knowledge base consists of a collection of rules, whose triggering depends on text patterns recognized within the user input. Even if they are an interesting and promising idea, recent statistics detected poor usage and a relatively short lifetime. This paper suggests an improvement of the chatterbot technology, based on the implementation of a more proactive dialogue behavior. A chatterbot enhanced with proactivity can be regarded as an intelligent conversational agent which is generally characterized by a more complex implementation approach but provides more efficient dialogue control through mixed-initiative strategies. By comparing chatterbots to finite state machines a formal definition of proactive chatterbots is reached and a standard implementation methodology is suggested. Finally, a case study discussing an example implementation of a virtual risk management advisor is provided.