Humorized Computational Intelligence towards User-Adapted Systems with a Sense of Humor

This paper investigates the role of humor in non-task oriented (topic restriction free) human-computer dialogue, as well as the correlation between humor and emotions elicited by it in users. A joke-telling conversational system, constructed for the needs of this research, was evaluated by the users as better and more human-like than a baseline system without humor. Automatic emotive evaluation with the usage of an emotiveness analysis system showed that the system with humor elicited more emotions than the other one, and most of them (almost 80%) were positive. This shows that the presence of humor makes computers easier to familiarize with and simply makes users feel better. Therefore, humor should be taken into consideration in research on userfriendly applications, as it enhances the interaction between user and system. The results are discussed and our concept of a user-adapted humor-equipped system is presented.

• Type: Conference
• Year: 2009
• Where: EVOW
• Authors: Pawel Dybala, Michal Ptaszynski, Rafal Rzepka, Kenji Araki
• Keywords: Artificial Intelligence, EVOW 2009, Humor, Humor Makes Computers, Joke-telling Conversational System