Distance Courseware Discrimination Based on Representative Sentence Assaying

In order to train distance learning students the discernment abilio, teachers often suggest to them web courseware on some specific topics, such as a controversial social issues, with different view points. Traditional discriminating strategies based on simple keyword matching often lead to low accuracy of discrimination. This paper proposes a method called DRSA (Discriminating via Representative Sentence Assaying), which is based on a five-stage process: extracting representative phrases, calculating characteristic array, mining threshold array, objective judgment, and subjective judgment. Experimental results show that our algorithms are very efficient in discriminating documents into positive and negative views.