Automatic Concept Extraction for Domain and Student Modeling in Adaptive Textbooks

• Published in: International journal of artificial intelligence in education Vol. 31; no. 4; pp. 820 - 846
• Main Authors: Chau, Hung, Labutov, Igor, Thaker, Khushboo, He, Daqing, Brusilovsky, Peter
• Format: Journal Article
• Language: English
• Published: New York Springer New York 01.12.2021; Springer; Springer Nature B.V
• Subjects: A festschrift in honour of Jim Greer; Adaptation; Annotations; Artificial Intelligence; Automation; Comparative Analysis; Computer Science; Computer Uses in Education; Computers and Education; Customization; Documentation; Educational Technology; Hypermedia; Information Retrieval; Keywords; Knowledge; Knowledge Level; Knowledge representation; Machine learning; Modelling; Natural Language Processing; Periodicals; Personalized learning; Prerequisites; Researchers; Subject specialists; Teaching Methods; Textbooks; Tutoring; User Interfaces and Human Computer Interaction; Concept annotation; Intelligent textbooks; Student modeling; Domain modeling; Concept extraction
• ISSN: 1560-4292; 1560-4306
• DOI: 10.1007/s40593-020-00207-1

The increasing popularity of digital textbooks as a new learning media has resulted in a growing interest in developing a new generation of adaptive textbooks that can help readers to learn better through adapting to the readers’ learning goals and the current state of knowledge. These adaptive textbooks are most frequently powered by internal knowledge models, which associate a list of unique domain knowledge concepts with each section of the textbook. With this kind of concept-level knowledge representation, a number of intelligent operations could be performed, which include student modeling, adaptive navigation support, and content recommendation. However, manual indexing of each textbook section with concepts is challenging, time-consuming, and prone to errors. Modern research in the area of natural language processing offers an attractive alternative, called automatic keyphrase extraction . While a range of keyphrase and concept extraction methods have been developed over the last twenty years, few of the known approaches were applied and evaluated in a textbook context. In this paper, we present FACE, a supervised feature-based machine learning method for automatic concept extractions from digital textbooks. This method has been created for building domain and student models that form the core of intelligent textbooks. We evaluated FACE on a newly constructed full-scale dataset by assessing how well it approximates concept annotations produced by human experts and how well it supports the needs of student modeling. The results show that FACE outperforms several state-of-the-art keyphrase extraction methods.