Scripting Affective Communication with Life-Like Characters in Web-Based Interaction Systems

نویسندگان

  • Helmut Prendinger
  • Sylvain Descamps
  • Mitsuru Ishizuka
چکیده

In this paper, we discuss scripting tools that aim at facilitating the design of web-based interactions with animated characters capable of affective communication. Specifically, two systems are developed. The SCREAM system is a scripting tool that enables authors to create emotionally and socially appropriate responses of animated characters. Content authors may design the mental make-up of a character by declaring a variety of parameters and behaviors relevant to affective communication and obtain quantified emotional reactions that can be input to an Animation Engine. While the default operations of a character’s ‘mind’ are based on psychological and sociological research, authors may easily modify and extend its rule set. In order to facilitate high-level scripting and connectivity with other web-based animated agent systems, the tool is written in a lightweight Java based Prolog system and Java. Connectivity is demonstrated by interfacing SCREAM with the our second system, MPML, an XML-style markup language that allows to control and coordinate the multi-modal appearance of synthetic characters. Affective communication with animated characters is illustrated by the implementation of a web-based casino scenario. Submitted to: Applied Artificial Intelligence Journal Statement: The authors certify that this work has not been published elsewhere and that it has not been submitted simultaneously for publication elsewhere. Abbreviated title: “Scripting Affective Communication with Life-like Characters” or if too long, “Scripting Affective Communication”

برای دانلود رایگان متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

e SCRIPTING AFFECTIVE COMMUNICATION WITH LIFE-LIKE CHARACTERS IN WEB-BASED INTERACTION SYSTEMS

In this paper, we discuss scripting tools that aim at facilitating the design of Web-based interactions with animated characters capable of affective communication. SpeciŽ cally, two systems are developed. The SCREAM system is a scripting tool that enables authors to create emotionally and socially appropriate responses of animated characters. Content authors may design the mental make-up of a ...

متن کامل

Social Computing Life-like Characters as Social Actors

Social Computing aims to support the tendency of humans to interact with computers as if they were veritable social actors. Technology that reinforces the bias toward social interaction by producing appropriate responses may improve the communication between humans and computational devices. We believe that the most natural way to realize social computing is by using life-like synthetic charact...

متن کامل

MPML and SCREAM: Scripting the Bodies and Minds of Life-Like Characters

In this paper, two systems will be described. First, we present an architecture for emotion-based agents, called SCREAM, that allows to encode affect-related processes for an animate character. Content authors may design the mental make-up of the agent by declaring a variety of parameters relevant to affective communication and obtain quantified emotional reactions. Second, we report on MPML, a...

متن کامل

MPML: a markup language for controlling the behavior of life-like characters

Animated agents have the potential to convey information in a more natural way than other media traditionally used on the world-wide web, such as text, audio, or video clips. They also allow for more natural styles of human–computer interaction than navigation through hypertext documents. In this paper, we will introduce the multi-modal presentation markup language (MPML), which is a powerful a...

متن کامل

Evolving Social Relationships with Animate Characters

In order to come across as life-like or animate, characters must change their attitudes (‘evolve’) as a consequence of their affective interaction histories with other agents. This paper describes a model of attitude and familiarity change that allows to model simple forms of evolving social relationships. We illustrate our model by means of two web-based interaction scenarios that feature anim...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

عنوان ژورنال:
  • Applied Artificial Intelligence

دوره 16  شماره 

صفحات  -

تاریخ انتشار 2002