Automatic text processing: the transformation, analysis, and retrieval of information by computer
Automatic text processing: the transformation, analysis, and retrieval of information by computer
PAT-tree-based keyword extraction for Chinese information retrieval
Proceedings of the 20th annual international ACM SIGIR conference on Research and development in information retrieval
Automatic thesaurus generation for Chinese documents
Journal of the American Society for Information Science and Technology
Exploratory Social Network Analysis with Pajek
Exploratory Social Network Analysis with Pajek
A new approach for constructing the concept map
Computers & Education
Mining e-Learning domain concept map from academic articles
Computers & Education
Concept Map Mining: A Definition and a Framework for Its Evaluation
WI-IAT '08 Proceedings of the 2008 IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology - Volume 03
Accumulating and visualising tacit knowledge of teachers on educational assessments
Computers & Education
Expert Systems with Applications: An International Journal
Hi-index | 0.00 |
Motivated by a long-term goal in education for measuring Taiwanese civic scientific literacy in media (SLiM), this work reports the detailed techniques to efficiently mine a concept map from 2years of Chinese news articles (901,446 in total) for SLiM instrument development. From the Chinese news stories, key terms (important words or phrases), known or new to existing lexicons, were first extracted by a simple, yet effective, rule-based algorithm. They were subjected to an association analysis based on their co-occurrence in sentences to reveal their term-to-term relationship. A given list of 3657 index terms from science textbooks were then matched against the term association network. The resulting term network (including 95 scientific terms) was visualized in a concept map to scaffold the instrument developers. When developing an item, the linked term pair not only suggests the topic for the item due to the clear context being mutually reinforced by each other, but also the content itself because of the rich background provided by the recurrent snippets in which they co-occur. In this way, the resulting instrument (comprised of 50 items) reflect the scientific knowledge revealed in the daily news stories, meeting the goal for measuring civic scientific literacy in media. In addition, the concept map mined from the texts served as a convenient tool for item classification, developer collaboration, and expert review and discussion.