Affect Detection and an Automated Improvisational AI Actor in E-drama.pdf

Affect Detection and an Automated Improvisational AI Actor in E-drama Li Zhang 1 , Marco Gillies 2 , John A. Barnden 3 , Robert J. Hendley 3 , Mark G. Lee 3 and Alan M. Wallington 3 1 School of Computing and Technology, University of East London, Dockland Campus, 4-6 University Way, London, E16 4LZ 2 Department of Computer Science, University College London, London, WC1E 6BT 3 School of Computer Science, University of Birmingham, Birmingham, B15 2TT L.Zhang@cs.bham.ac.uk Abstract. Enabling machines to understand emotions and feelings of the human users in their natural language textual input during interaction is a challenging issue in Human Computing. Our work presented here has tried to make our contribution toward such machine automation. We report work on adding affect-detection to an existing e-drama program, a text-based software system for dramatic improvisation in simple virtual scenarios, for use primarily in learning contexts. The system allows a human director to monitor improvisations and make interventions, for instance in reaction to excessive, insufficient or inappropriate emotions in the characters’ speeches. Within an endeavour to partially automate directors’ functions, and to allow for automated affective bit-part characters, we have developed an affect-detection module. It is aimed at detecting affective aspects (concerning emotions, moods, value judgments, etc.) of human-controlled characters’ textual “speeches”. The work also accompanies basic research into how affect is conveyed linguistically. A distinctive feature of the project is a focus on the metaphorical ways in which affect is conveyed. Moreover, we have also introduced how the detected affective states activate the animation engine to produce gestures for human- controlled characters. The description of our approach in this paper is taken in part from our previous publications [1, 2] with new contributions mainly on metaphorical language processing (practically and theoretically), 3