Identifying core concepts in educational resources

Abstract

This paper describes the results of a study designed to assess human expert ratings of educational concept features for use in automatic core concept extraction systems. Digital library resources provided the content base for human experts to annotate automatically extracted concepts on seven dimensions: coreness, local importance, topic, content, phrasing, structure, and function. The annotated concepts were used as training data to build a machine learning classifier as part of a tool used to predict the core concepts in the document. These predictions were compared with the experts' judgment of concept coreness.

Identifying the core concepts of pharmacology education

“…7,8 Core concepts have also been extracted from textbooks, either via page-by-page expert analysis 16,25 or more recently via data mining techniques. 37 The aim of this study was to develop proof-of-concept for a criterion-based method to identify, define, and unpack the core concepts of pharmacology as defined by pharmacology educators in Australia and New Zealand. This will have the dual benefit of providing the concepts for which concept inventories can be produced and providing the first steps toward a framework for the evidence-based curricular design of pharmacology courses.…”

“… 7 , 8 Core concepts have also been extracted from textbooks, either via page‐by‐page expert analysis 16 , 25 or more recently via data mining techniques. 37 …”

“…Expert groups or sub‐groups have been utilized to analyse survey responses and extract core concepts 7,8 . Core concepts have also been extracted from textbooks, either via page‐by‐page expert analysis 16,25 or more recently via data mining techniques 37 …”

Identifying the core concepts of pharmacology education: a global initiative

“…Most disciplines have used a Delphi method, involving a group of experts completing cycles of surveying and refinement until consensus is reached (Boneau, 1990;Brownell et al, 2014;Landrum, 1993;Merkel, 2012;Parekh et al, 2017;Wright & Hamilton, 2008). Core concepts have also been extracted from textbooks, either via page-by-page expert analysis (Zechmeister & Zechmeister, 2000) or via data-mining techniques (Foster et al, 2012).…”

Scaffolding Beginning Research Students Using Open Source Tools

“…Concept extraction, 12,16 single-and multi-document summaries, 16 clustering and classification, 8 and collection understanding 9,15 are means for identifying higher-level domain concepts and to acquire unified view of a research topic. Performing these tasks requires programming expertise with Python and NLTK library for natural language processing.…”