Making Learning Fun EDrama Project Online dramatic improvisation

Making Learning Fun E-Drama Project On-line dramatic improvisation (role-play) with Artificial Intelligence enhancements John Barnden, University of Birmingham Amanda Oldroyd, BT Group CTO Jemima Cattel, Hi 8 us Midlands Ltd Jonnie Turpie, Maverick TV Ltd

Presentation Structure § § § Introduction Benefits of software AI developments User study feedback 3 D interfaces Insights

Introduction: What is E-drama In this presentation, e-drama means dramatic improvisation or role-play where the actors don’t work on a real stage but instead sit at computers and operate virtual on-screen characters. Actors type in “speeches” which are shown in speech bubbles. There is usually also a director who sits at another computer. from a version of the edrama system from Hi 8 us – already a proven tool Usually a loose scenario is specified, such as a School Bullying scenario, or an educational scenario (History, Science, etc. )

Seminar Themes Addressed § Making learning more motivating and fun § Challenging game-like activities § Creativity § Various types of hard-to-reach learner, and shy or disaffected learners § Next-generation e-learning

The Point of E-Drama § Complements the use of live improvisation in learning and creativity. § It is anonymous and therefore less intimidating, and also more motivating: § 92% of school students in recent test found edrama less nervous-making § 81% found it more enjoyable overall

Plan of Rest of Talk § Directorial interventions § Desirability of semi-automating them § Current developments towards this § Points from recent user-testing § More advanced graphics

Directorial Intervention § Director can intervene to keep the drama on fruitful tracks, incl. with regard to expressed emotions. § Director can send (written) messages to all actors or “whisper” to an individual one. § Director can introduce a bit-part

A Reason for Directorial Intervention § Emotional and other “affective” expression is inappropriate, excessive or lacking. -- Swearing or out-of-character rudeness -- Excessive anger or hostility -- Lack of expected embarrassment -- Lack of expected concern about someone’s emotional state

Artificial Intelligence and Human. Language Processing § Problem: demands on director are substantial. § Partial automation would be beneficial. § We are implementing § automated detection of affect (e. g. , emotion), hence § automated directorial interventions, incl. introduction of automated affect-sensitive bit-part characters § Will allow more widespread and untrained use. § Scalability, distributed interaction

Artificial Intelligence, contd § The automation is not intended or expected to make the overall experience better. § It would be a good result if it made it not too much worse!

Automated Bit-Part Character § Em. Eliza is our first research-prototype program for operating an automated affect-sensitive bitpart character: § It detects affective aspects of the other characters’ speeches, makes certain types of inference, and makes short response speeches. § Operating in our demo here.

Em. Eliza – A Bit-part Character Actor Human-acted character Em. Eliza’s perception of that character I am scared of Mayid. He is a bully. I can't move my legs and it's killing me! boo hoo *cries* I am going to hit you. [A LITTLE BIT SCARED] [VERY SCARED] [A LITTLE BIT THREATENING] Em. Eliza’s character’s replies Why not let your mum talk to his parents Oh, dear, Please be more brave. Help will be here soon. You look like a real trouble maker.

User Testing: Pilot Run Swanshurst School, Birmingham, May 2005 § Methodology: 39 subjects were involved over two days. Each of them participated in both of the two selected scenarios, namely School Bullying and Crohn’s Disease, with/without Em. Eliza. One Result: Nobody suspected that

Some Preliminary User-Testing Results § When a certain character “Dave” was played by Em. Eliza: § Little effect on the proportion of (other) actors who regarded Dave as being poorly played. § NB: substantial effect on various other measures and on actors’ comments.

Having Em. Eliza as Dave, contd. § Did raise the proportion of actors who got bored from 9% to 18% …. BUT § Reduced the proportion of actors saying they disliked playing their own character from 24% to 12%. § Raised the proportion of actors who wanted the improv to be longer

Adding 3 rd Dimension § Dealing with sophisticated user groups: § Experience with gaming technologies § High expectations § 3 d characters and customisation § 3 d virtual environments

Realtime 3 D Rendering § Virtual world rendering architecture (TARA): realtime 3 D engine for avatars and backgrounds § 3 D virtual characters with customisation and animation libraries

Expressive Behaviour - Demeanour System § Generating expressive body language for virtual characters in order to create emotionally richer on-line experiences § Behaviour is generated based on a set of parameters representing emotion, mood, personality etc. § Customise characters’

Automated Behaviour linked to profiles § Profiles related to the key character types in the role-play structure § Each avatar animates automatically in response to other characters § No user intervention required during roleplay profiles Main character Friend Arbitrator Antagonist Bit-parts

Review § Hi 8 us edrama is already a proven tool, used by a range of users in a range of settings. § Building on established role-play techniques – online. § AI enhancements provide the opportunity to enable more widespread and untrained use. § 3 D enhancements build on existing software to provide a richer user experience

Benefits of E-Drama: from Learner Point of View “It was really fun and a change from ordinary activities to help understand bullying and diseases” “I preferred using this to having a conversation face to face because you can almost ‘hide’ behind the character”

Benefits of E-Drama: from Teacher Point of View § Releases learner creativity, free from peer pressure § Encourages learner involvement § Motivates study of the included background material § Low overhead for teachers to become proficient in running It’s fun for the teacher too!: can be guide, actor or sessions

Seminar Themes Addressed § Making learning more motivating and fun § Challenging game-like activities § Creativity § Various types of hard-to-reach learner, and shy or disaffected learners § Next-generation e-learning

Thank you Questions http: //www. cs. bham. ac. uk/research/projects/edrama/