Research on a new automatic generation algorithm of concept map based on text analysis and association rules mining

• Published in: Journal of ambient intelligence and humanized computing Vol. 11; no. 2; pp. 539 - 551
• Main Authors: Shao, Zengzhen, Li, Yancong, Wang, Xiao, Zhao, Xuechen, Guo, Yanhui
• Format: Journal Article
• Language: English
• Published: Berlin/Heidelberg Springer Berlin Heidelberg 01.02.2020; Springer Nature B.V
• Subjects: Algorithms; Artificial Intelligence; Computational Intelligence; Concept mapping; Data mining; Datasets; Education; Educational materials; Engineering; Learning; Methods; Natural language processing; Original Research; Questions; Robotics and Automation; Students; Technology assessment; Text analysis; Text categorization; User Interfaces and Human Computer Interaction; Visualization; Automatic generation; Concept map; Educational data mining; Text analysis; Association rules mining; Text classification
• ISSN: 1868-5137; 1868-5145
• DOI: 10.1007/s12652-018-0934-9

As an important knowledge visualization tool, concept map has become a research hotspot in educational data mining. Traditional concept map generation algorithms are difficult to generate concept maps quickly because of their strong reliance on experts’ experience. A hybrid TA-ARM algorithm for automatic generation of concept map based on text analysis and association rule mining is proposed. The TA-ARM algorithm fully considers the association rules between concepts, uses the text classification algorithm in text analysis technology instead of manually classify the questions into concepts, and combines the association rule mining method to generate concept maps. The experimental result shows that the TA-ARM algorithm can automatically and rapidly generate the concept map, which not only reduces the impact of outside experts, but can also dynamically adjusts the concept map based on the parameters such as the threshold of confidence between test questions. The concept map generated by the TA-ARM algorithm expresses the association rules between the concepts and the degree of closeness through the associated pairs and relevant degree, and can clearly show the structural associations between concepts. The contrast experiment shows that the quality of the concept map automatically generated by the TA-ARM has a high quality and can visualize the associations between concepts and provide optimization and guidance for knowledge visualization.