The objective of this study was to investigate if an e-learning environment may use measurements of the user's current motivation to adapt the level of task difficulty for more effective learning. In the reported study, motivation-based adaptation was applied randomly to collect a wide range of data for different adaptations in a variety of motivational states. This data was then utilised to extract rules for an adequate motivation-based adaptation to maximise expected learning success. A learning classifier system was used for the data analysis, generating rules for suitable and unsuitable adaptations based on current user motivation data. We extracted a set of twelve rules which suggest particular adaptation strategies based on real-world data. These rules could generally be embedded into existing psychological theories, namely the Zone of Proximal Development and the Yerkes-Dodson Law. In future research, we intend to evaluate these rules on further studies and develop concrete sets of adaptation strategies based on user motivation measurements.
IntroductionE-learning is a large part of the current educational process. A growing number of educational institutions utilise e-learning, such as learning games suitable to teach a particular (small) topic, online language courses, and even entire university programs using virtual classrooms. Some of these e-learning environments, free and commercial, are used in real instructional settings. Self-study language programs are a well-known example. However, most of these instructional systems still employ a 'one-size-fits-all' philosophy, where every learner, irrespective of their individual abilities and needs, is presented with the same content in the same way (e.g., Rey, 2009). Although these learning environments may help students to learn, adapting e-learning environments to the individual needs of each student may help learners reach their learning goal even more quickly and effectively (e.g., Chen, Lee & Chen, 2005;Shute & Towle, 2003).These adaptive e-learning environments have been researched for quite a while. According to Mödritscher, Garcia-Barrios and Gütl (2004), the macro-adaptive approach, which allows the adaptation of some main components, can be traced back to the 1970s. Current developments in the field of computer science make it possible to 1120 Australasian Journal of Educational Technology, 2012, 28(7) build and thoroughly test ever more complex learning environments, which may take even more adaptation criteria into account. One of these criteria is the learner's current motivation.Motivation is an internal condition that activates, energises, and directs behaviour. It has been shown to correlate with learning performance in several studies. Schiefele, Krapp and Winteler (1992) concluded from a meta-analysis that measured interest can predict school achievement. Using a program that teaches tenth-grade students genetics, Song and Keller (2001) showed that a motivationally adaptive strategy promised a significantly higher performance and effi...