Abstract—The popularity of web based learning has led to the development of many learning object repositories that store high quality learning materials. High quality learning materials are expensive to create. So it is very important to ensure reuse of learning materials. Reuse of learning materials are made possible by semantically tagging them with standard metadata. In all available learning object repositories the tagging is done manually. Manual annotation is time taking and labor intensive activity. In this paper, we have explored the feasibility of tagging learning materials automatically with IEEE LOM 9.0 metadata specification. Here, we present machine learning approach using k-nearest neighborhood and back propagation neural network to automatically identify the subject of learning materials. The classifier is tested & result shows about 84% & 93% accuracy for back propagation neural network & K-NN resp.
Index Terms—BPN, classification, KNN, learning object.
Siddhartha Kumar Arjaria is with the Maulana AzadNational Institute of Technology Bhopal,462051 India (e-mail: arjarias@ gmail.com).
Devshri Roy is with the Maulana AzadNational Institute of Technology Bhopal, 462051 India(e-mail: droy.iit@ gmail.com)
Cite: Siddhartha Kumar Arjaria and Devshri Roy, "Learning Content Management Using Machine Learning," International Journal of Information and Education Technology vol. 2, no. 5, pp. 472-475, 2012.