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...
This paper investigates XCS performance on a scarce and noisy artificial and a real-world data set. The real-world data set is derived from an E-Learning study, in which motivation was correlated with the adaptation of difficulty. The artificial data set was generated to evaluate if XCS can be expected to mine information from the real-world data set. By adding sparsity and noise to the artificial data set, mimicking the properties of the real-world data set, we show that XCS can handle scarce and noisy data well. We furthermore show that the extracted structure contains problem-relevant information, and that revealed structures in the real-world data correspond to actual psychological learning theories. Thus, the contributions of the paper are twofold: (1) We show that XCS can mine highly scarce and noisy data; and (2) the results suggest that the current motivational state of the user may be utilized to adapt an E-Learning program for improving learning progress.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.