QuizMASter – A Multi-Agent Game-Style Learning Activity Mark Dutchuk Vancouver Island University, Canada Khalid Aziz Muhammadi Government of Alberta, Canada

QuizMASter – A Multi-Agent Game-Style

Learning Activity

Edutainment 2009 Banff, Canada August 9-11, 2009

Presented by: Dr. Fuhua (Oscar) Lin

Some Problems in Game-based Learning

Okonkwo & Vassileva (2001) showed that while educational games can be successful at motivating students to play them, their effect on actual learning might be small.

Kirriemuir et al. (2004): among other reasons, educational games often fail because they are too simplistic when compared with commercial video games, too repetitive, and the tasks do not support progressive understanding.

Okonkwo & Vassileva (2001) showed that while educational games can be successful at motivating students to play them, their effect on actual learning might be small.

Kirriemuir et al. (2004): among other reasons, educational games often fail because they are too simplistic when compared with commercial video games, too repetitive, and the tasks do not support progressive understanding.

EduTainment 2009 2Athabasca University

Our Research Goal

To study how to to construct effective educational games with TV-show style for e-learning through using the multi-agent systems (MAS) approach.


Related WorkMCOE (Multiagent Co-operative Environment)

(Giraffa et al., 1998)simulates a lake environment.learners learn the effects of pollution & try

to control it.Includes

reactive agents such as fish and plants, and

cognitive agents including a tutoring agent & a virtual ‘ecologist’.


Related Work (Contd..)REAL (Reflective Agent Learning Environment)

(Bai & Black, 2006) is an agent-based learning environment provides a framework for simulation game scenarios, providing an Expert agent that contains the knowledge

about the system being simulated a Reflective agent to model what the learner

‘knows’ about his or her environment a Pedagogical agent compares the Reflective

agent’s knowledge with that of the Expert agent’s and adjusts it teaching strategy.


Our Approach in QuizMASter

Multi-Agent System-based educational game that would help students learn their course material through friendly competition

Use Pedagogical Agents to provide feedback & motivationto assess learners’ emotional states

through examining learner’s standing, response timing, and history, and banter; and

to provide appropriate feedback to students in order to motivate them


QuizMASter’s Functional Requirements

Similar to a TV game show, where a small group of contestants compete by answering questions presented by the game show host.

Contestants score points by correctly answering questions before their opponents do.

Questions are drawn from a learning management system database and presented to player’s one question at a time.

The answer given, the length of time taken to respond are transmitted back to a central agent.

Scores will be tallied, and the feedback on a player’s standing will be provided to motivate the player.


The Architectural Design


Player Agent

Host Agent

Banter Session

Bonding

Scoring Subsystem

Tasks of AgentsCalculating Contestant Standing:

Assumption:a contestant that is winning is sufficiently engaged, and that those in last place are somewhat unhappy with, or

uninterested in their performance in the game. Based on such assumptions we use the contestant’s

current standing as a factor when calculating their attitude

Recording Response Timing and History that then be analyzed and compared with the other players.

Examining the interaction between the host and the player during what we call ‘banter’ sessions to infer a user’s state from their conversations.


Player AgentThe responsibilities of the Player agent:

Assess and maintain the contestant’s emotional state

Receive and display questionsCalculate response timingSend Response objects back to the

Host agent


The Player Agent


The Host Agent -- Responsibilities

Present questions

Provide feedback to the contestants

Engage in banter sessions with contestants

Attempt to ‘bond’ with the contestant, by displaying appropriate emotion.

Maintain an high level of interest/excitement

Scorekeeping


The Host Agent --- Banter Session

Periodically throughout the game (typically after every 2-3 questions) the Host agent will engage in ‘banter’ with a contestant.

The contestant is chosen based on:The contestant with the lowest ‘emotion’

factorThe winner after the current ‘round’ of

playRandom selection when no clear data is

availableEduTainment 2009 13Athabasca University

The Host Agent -- Bonding

Each Host agent attempts to bond with its contestant by celebrating their success ‘sharing the pain’ of an incorrect

response.

This is accomplished by presenting an appropriate face to the contestant. In an attempt to maintain a positive attitude, the Host agent will normally display a ‘happy’ face.


The Host Agent – Scoring

is responsible for processing response objects:

the answerstiming emotional state information.

calculating scores standings for current game


Host Agent Interface


ConclusionsAgent autonomy is the principle reason

for choosing MAS as the game control system (Aylett and Luck, 2000)

The current version of QuizMASter provides basic perception and feedback systems to assess a player’s attitude during game-play and provide appropriate responses. It has allowed us to identify and study several implementation issues.


Future WorkVoice recognition:

Currently our prototype Host agent provides text-only interactions.

FreeTTS3 speech synthesis software and Sphinx-44 voice recognition software are being considered to provide natural language communications between contestants and the QuizMASter host.

This would provide a less distracting interface for contestants, while permitting QuizMASter to identify keywords directly from the contestant’s speech.


Future Work (Contd..)Emotion: Software is currently available

that is able to detect emotions based on facial recognition. Software such as this could supplement the conversation-based perception subsystem used by the current version

Implement QuizMASter in Sun’s Wonderland 3D virtual environment. The Wonderland environment will improve our system substantially by adding graphics, animation, and sound elements.

Incorporating Adaptive Features into QuizMASter.


MAS for adaptive immersive GBL

EduTainment 2009Athabasca University 20

Thank You!

Intelligent Educational Systems Research Group (IESRG)

Athabasca University, Canada

http://oscar.athabascau.ca


Documents

QuizMASter – A Multi-Agent Game-Style Learning Activity Mark Dutchuk Vancouver Island University, Canada Khalid Aziz Muhammadi Government of Alberta, Canada