Intelligent Adaptation of Digital Game-Based Learning Brian Magerko Adaptive Digital Media Lab Georgia Institute of Technology 686 Cherry St., Atlanta, GA 30332 404.894.2739 magerko@gatech.edu Carrie Heeter Games, Entertainment & Learning Lab Michigan State University 419 Comm. Arts Bldg., East Lansing, MI 48824 415.235.4766 heeter@msu.edu Joe Fitzgerald Matrix: Center for Humane Arts, Letters and Social Sciences Online 417 Natural Sciences Bldg. East Lansing, MI 517.884.2475 fitzgerald.jt@gmail.com Ben Medler Adaptive Digital Media Lab Georgia Institute of Technology 686 Cherry St., Atlanta, GA 30332 404.894.2739 benmedler@gatech.edu ABSTRACT Games for learning cannot take the same design approach as games when targeting audiences. While players of entertainment games have the luxury of choosing games that suit them, students using digital games for learning typically have a single game for them to learn from, regardless of whether or not it fits their playing style or learning needs. We contend that this problem can be addressed by creating games that identify the kind of player-learner using the game and adapts itself to best fit that individual. These adaptive games can specialize themselves according to a student’s learning needs, gameplay preferences, and learning style. We present a prototype mini-game, called S.C.R.U.B., which employs this method for teaching microbiology concepts. Categories and Subject Descriptors H.5.2 User Interfaces---User-centered design, I.2.1 Applications and Expert Systems---Games, K.3.1 Computer Uses in Education General Terms Design, Human Factors, Experimentation Keywords User modeling, adaptive games, player types 1. INTRODUCTION Games for entertainment are voluntary experiences; players choose when, where and what kind of games they are going to play. If a game does not appeal to a player, the player simply avoids playing it. Games for learning, on the other hand, tend to be required as part of a school curriculum or corporate training program. Players of these games have little choice as to what kind of game they will be learning from. Therefore, a single game for learning typically has a much more diverse player audience. Games for learning lack the luxury of vast budgets yet must serve everyone in the class, not just interested players. A different approach in game design needs to be taken to match a digital game-based learning experience to player motivations. Many educational theories classify different types of learners, such as Dunn and Dunn’s learning style inventory [1] and Kolb’s experiential learning styles [2]. A recent literature review identified 71 distinct learning style models [3]. Some models assume learning style is a fixed personality trait while others view learning style as context- specific state. Motivation is a central correlate to learning. Students who are more motivated are more likely to learn. Successful commercial games attract players because they are fun and engaging. Consequently, a key reason teachers consider using learning games in their classes is in hopes of motivating their students. Within the very strict bounds of limited time and extensive curricular requirements, K-12 classroom teachers try to present material in different ways to get a particular point across in order to communicate that knowledge to different kinds of learners in the class (e.g. lecture, hands-on problem solving, experimentation, homework, group projects, etc.). Accommodating different learning styles in the classroom is accomplished by having the entire class engage in some activities for each learning type. A digital game might serve some types of learners very well. Other students will be left behind simply because their learning needs are not met by the particular design of the game being played. However, there is possibly a better approach to digital game-based learning: a single game that Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. FuturePlay 2008, November 3-5, 2008, Toronto, Ontario, Canada. Copyright 2008 ACM 978-1-60558-218-4…$5.00.