Learning to identify educational materials
Samer Hassan, Rada F. Mihalcea · ACM Transactions on Speech and Language Processing · 2008
In this article, we explore the task of automatically identifying educational materials by classifying documents with respect to their educational value. Through experiments carried out on a dataset of manually annotated documents, we show that the generally accepted notion of a learning object's “educational value” is indeed a property that can be reliably assigned through automatic classification. Moreover, an analysis of cross-topic and cross-domain portability shows that the automatic classifier can be ported to other topics and domains, with minimal performance loss.