Machine Learning Assessment System for Modeling Patterns of Student Learning

We have developed and validated layered analytic models of how high school and university students construct, modify and retain problem solving strategies as they learn to solve science problems online. First, item response theory modeling is used to provide continually refined estimates of problem solving ability as students solve a series of simulations. In parallel, student’s strategies are modeled by self-organizing artificial neural network analysis, using the actions that students take during problem solving as the classifying inputs. This results in strategy maps detailing the qualitative and quantitative differences among problem solving approaches. Hidden Markov Modeling then develops learning trajectories across sequences of performances and results in stochastic models of problem solving progress across sequential strategic stages in the learning process. Using this layered analytical approach we have found that students quickly adopt preferential problem solving strategies, and continue to use them up to four months later. Furthermore, the approach has shown that students working in groups solve a higher percentage of the problems, stabilize their strategic approaches quicker, and use a more limited repertoire of strategies than do students working alone.

Learning Sociology in a Massively Multistudent Online Learning Environment

Is it possible to enhance student learning in Sociology 101 by staging simulated field studies in a MMOLE (massively mufti-student online learning environment) modeled after successful massively multiplayer online games (MMOG) such as Eve and Lineage? Lacking such a test option, the authors adapted an existing (MMOG) -"The Sims Online" - and conducted student exercises in that virtual environment during two successive semesters. Guided by questions keyed to course objectives, the sociology students spent ten hours observing online interactions in TSO and produced essays revealing different levels of analytical and interpretive ability. The students in an advanced course on deviance performed better, with the most detailed reports focusing on scamming, trashing, and tagging. Although there are no technical obstacles to the formation and deployment of a sociology MMOLE able to serve hundreds of thousands of students, such a venture would have to solve major financial and political problems

simSchool and the Conceptual Assessment Framework

simSchool is a game-based simulation developed with funding from the Preparing Tomorrow’s Teachers to Use Technology (PT3, 2003) program of the United States Department of Education. The simulation provides users with a training environment for developing skills such as lesson planning, differentiating instruction, classroom management, special education, and adapting teaching to multiple cognitive abilities. This chapter uses simSchool as an example to present and discuss an application of the Conceptual Assessment Framework (CAF) of (Almond, Steinberg, & Mislevy, 2002) as a general model for building assessments of what users learn through games and simulations. The CAF organizes the theories of teaching as well as the inferential frameworks in simSchool that are used to provide feedback to players about their levels of knowledge and abilities as teachers. The framework is generally relevant and useful for planning how to assess gains made by users while playing games or using simulations.

Reliving the Revolution

Students need to learn the critical thinking of history, yet they rarely have opportunities to authentically simulate historic inquiry. Research has suggested the pedagogical potential for using augmented reality (AR) games—location-based games that use wireless handheld devices such as PDAs to provide virtual game information in a physical environment. The novel AR game, Reliving the Revolution (RtR), was created as a model for studying how AR games can engage students in interpretive, collaborative, and problem-solving activities. In this chapter, the game is introduced and main results of the initial iterative tests are discussed, including what went wrong and how the game was redesigned to better support deeper engagement and historical thinking and learning.

Lessons Learned Modeling "Connecting Teaching and Learning"

While designing a web-based simulation to provide practice for teacher education students as they sought to master the complex skills expected of them as they develop work samples, the authors learned eight important lessons during the development of Cook School District. Work samples are a methodology for helping students learn to analyze their teaching by seeking connections between their work and student achievement. Cook School District serves as a site where teacher candidates begin the arduous process of learning to determine which strategies of instruction and assessment will result in greater student growth. The four years required to develop the simulation brought home eight lessons, often painfully acquired, that are shared with readers. Learning and teaching are not inherently linked. Much learning takes place without teaching, and indeed much teaching takes place without learning (Wenger, 1998).

Online Games for 21st Century Skills

As foreseen by visionaries in the 20th century, mastery of the dynamic processes that underpin the acquisition and manipulation of knowledge is quickly becoming a critical capability in the 21st century. Our formal educational systems do not tend to facilitate the development of these capabilities, yet people of all ages are developing them via a variety of digitally-mediated mechanisms. Online games offer one area of exploration for spontaneously-occurring phenomena that represent the natural development of such literacy. This chapter reviews the need for 21st-century skills and illuminates existing digital domains in which these skills develop organically. Peering through the window of the present into the future, we present a view that envisioning change means taking a long look at what is working now, regardless of whether that activity is taking place in a formal setting or within entertainment-based worlds where the skills are mandatory for mastery, but learned incidentally through play.

Designing Online Games Assessment as

Online retailers make successful use of sophisticated online tracking mechanisms to profile their customers in order to understand their buying habits. Online multiplayer games make use of similar technologies to keep track of gamers’ activities, for better management of in-game resources and to settle disputes. However, educators looking to online games as a learning tool lack a similarly powerful strategy to help them reconstruct users’ gaming decisions in order to understand the learners and make effective use of games as teaching/learning tool. Moreover, it is necessary to develop an assessment component for online games to measure its effectiveness, or the return of investment. This chapter outlined a strategy to design the much needed assessment into online games as “information trails.”

Building Artificially Intelligent Learning Games

The idea of digital game-based learning (DGBL) is gaining acceptance among researchers, game designers, educators, parents, and students alike. Building new educational games that meet educational goals without sacrificing what makes games engaging remains largely unrealized, however. If we are to build the next generation of learning games, we must recognize that while digital games might be new, the theory and technologies we need to create DGBL has been evolving in multiple disciplines for the last 30 years. This chapter will describe an approach, based on theories and technologies in education, instructional design, artificial intelligence, and cognitive psychology, that will help us build intelligent learning games (ILGs).

Developing an Online Classroom Simulation to Support a Pre-Service Teacher Education Program

Evaluations of our pre-service teacher education program identified a need to provide more classroom based experience for our students. This motivated us to embark on the journey of developing an on-line classroom simulation. The establishment of a team and the different areas of expertise we brought to the project resulted in a theoretically sound response to this challenge. In this chapter we share some of our insights from our experiences over the past three years working on this project. In particular we focus on the key stages in the development of the software, the roles we assumed and the lessons we learned.

Perspectives from Multiplayer Video Gamers

The purpose of this study is to determine whether multiplayer video gamers perceive that playing video games can increase higher order thinking skills such as motivation, problem-solving, communication, and creativity. Multiplayer video gaming allows participants the opportunity to collectively discuss problems with other players, find solutions and accomplish objectives. This study was used as a barometer to determine if multiplayer gamers perceived that playing multiplayer games had educational value. This research specifically sought to verify whether multiplayer video gamers perceived that higher-order thinking skills such as motivation, communication, problem-solving, and creativity were increased by playing multiplayer video games. The bulk of respondents reported that they somewhat felt there was learning occurring in all of these areas.