A term matching strategy for item-banks integration

Term matching is one of applications of pattern matching for comparing strings. This paper presents a strategy of term matching based on a tree structure for integrating item-banks. An item-bank consists of question items from which the contents are connected to. Contents of a text book are divided into concepts, followed by the tree structure, while each node contains terms that describes the concepts. Comparing the terms of question items and contents, item-banks can be integrated. To evaluate the performance of the proposed method, contents of two grades have been used on the learning process. The experimental results showed that the proposed algorithm can provide an extremely high quality result in terms of both the relevance of items and the computation time in Chinese item sets. In addition, the experimental results also showed that the accuracy rate of the item-bank described herein ranges from 93.3% to 94.8%.