An automated syllabus digital library system for higher education in Ireland

Purpose – With the significant growth in electronic education materials such as syllabus documents and lecture notes, available on the internet and intranets, there is a need for robust central repositories of such materials to allow both educators and learners to conveniently share, search and access them. The purpose of this paper is to report on the work to develop a national repository for course syllabi in Ireland. Design/methodology/approach – The paper describes a prototype syllabus repository system for higher education in Ireland, which has been developed by utilising a number of information extraction and document classification techniques, including a new fully unsupervised document classification method that uses a web search engine for automatic collection of training set for the classification algorithm. Findings – Preliminary experimental results for evaluating the performance of the system and its various units, particularly the information extractor and the classifier, are presented and discussed. Originality/value – In this paper, three major obstacles associated with creating a large-scale syllabus repository are identified, and a comprehensive review of published research work related to addressing these problems is provided. Two different types of syllabus documents are identified and describe a rule-based information extraction system capable of extracting structured information from unstructured syllabus documents is described. Finally, the importance of classifying resources in a syllabus digital library is highlighted, a number of standard education classification schemes are introduced, and the unsupervised automated document classification system, which classifies syllabus documents based on an extended version of the International Standard Classification of Education, is described.