Automatic Syllabus Classification

Syllabi are important educational resources. However, searching for a syllabus on the Web using a generic search engine is an errorprone process and often yields too many non-relevant links. In this paper, we present a syllabus classifier to filter noise out from search results. We discuss various steps in the classification process, including class definition, training data preparation, feature selection, and classifier building using SVM and Na¨ıve Bayes. Empirical results indicate that the best version of our method achieves a high classification accuracy, i.e., an F1 value of 83% on average.

Main Author:	Yu, Xiaoyan
Other Authors:	Tungare, Manas, Fan, Weiguo, Perez-Quinones, Manuel, Fox, Edward, Cameron, William, Teng, GuoFang, Cassel, Lillian
Language:	English
Published:	2007
Online Access:	http://ezproxy.villanova.edu/login?url=https://digital.library.villanova.edu/Item/vudl:175143