استفاده از تکنیک های داده کاوی ساخت نقشه های مفهومی به طور خودکار برای سیستم یادگیری انطباقی

It is obvious that to construct concept maps for providing the learning guidance to learners is an important research topic of adaptive learning systems. Because the existing method to construct concept maps only considers the association rules that questions are not correctly answered, it will miss some information about questions that are correctly answered by the learners. Moreover, the existing method also has the drawback that it will build unnecessary relationships or lose some relationships between concepts in the constructed concept maps. In this paper, we present a new method to automatically construct concept maps based on data mining techniques for adaptive learning systems. The proposed method can overcome the drawbacks of the existing method. It provides us a useful way to automatically construct concept maps in adaptive learning systems

In recent years, some researchers focused on the research topics of adaptive learning systems (Bai and Chen, 2008a, Bai and Chen, 2008b, Bai and Chen, 2008c, Bai and Chen, 2008d, Carchiolo et al., 2002, Chen and Bai, 2009, Hwang, 2003, Lee et al., 2009 and Novak, 1998). Bai and Chen (2008a) presented a method for evaluating student learning achievement using fuzzy membership functions and fuzzy rules. Bai and Chen (2008b) presented a method for automatically constructing concept maps based on fuzzy rules for adaptive learning systems. Bai and Chen (2008c) presented a method for automatically constructing grade membership functions for students’ evaluation for fuzzy grading systems. Chen and Bai (2009) presented a method for learning barrier diagnosis of learners based on fuzzy rules. Carchiolo et al. (2002) presented a method for dealing with adaptive formative paths in a web-based learning environment. Hwang (2003) presented a method for applying the conceptual map model for developing intelligent tutoring systems. Novak (1998) presented a method for using concept maps as facilitative tools in schools and corporations. To construct concept maps for providing the learning guidance to learners is an important research topic of adaptive learning systems. Bai and Chen (2008b) presented a method for automatically constructing concept maps based on fuzzy rules. Lee et al. (2009) presented a method to automatically construct concept maps for conceptual diagnosis of e-learning. Lee et al. used the Apriori algorithm (Agrawal & Srikant, 1994) for automatically constructing concept maps and proposed the remedial-instruction path (RIP) algorithm to build an intelligent concept diagnostic system (ICDS). However, Lee et al.’s method (2009) for automatically constructing concept maps has the following drawbacks: (1) Because it only considers the association rules that questions are not correctly answered, it will miss some information about questions that are correctly answered by the learners. (2) It will build unnecessary relationships or lose some relationships between concepts in the constructed concept maps. In this paper, we present a new method to automatically construct concept maps for adaptive learning systems based on data mining techniques to overcome the drawbacks of Lee et al.’s method (2009). The proposed method constructs concept maps based on the analysis of concept maps and the data mining techniques. It provides a useful way to construct concept maps for adaptive learning systems. The rest of this paper is organized as follows: In Section 2, we briefly review Lee et al.’s method (2009) for automatically constructing concept maps. In Section 3, we present a new method to automatically construct concept maps based on the analysis of concept maps and the Apriori algorithm (Agrawal & Srikant, 1994) for adaptive learning systems. In Section 4, we use an example to illustrate the process of automatically constructing concept maps based on the proposed method. The conclusions are discussed in Section 5.

In this paper, we have presented a new method for automatically constructing concept maps based on data mining techniques for adaptive learning systems. The proposed method considers the association rules that questions are not correctly answered and the association rules that questions are correctly answered for constructing concept maps. The proposed method overcomes the drawback of Lee et al.’s method (2009) and gets more reasonable results for constructing concept maps in adaptive learning systems. It provides a useful way to automatically construct concept maps for adaptive learning systems.