earticle

영어

Identification of analysis classes is a critical design decision to be made early in the design phase in software development. Although incorrect identification of analysis classes can diminish the quality of a whole software design, it still heavily relies on the expertise and experience of the developer and has been ad-hoc. The majority existing works on identification of analysis classes focus on the rule-based approaches. However, the rule-based approaches which are used for analyzing sentence structures cannot be adopted for the language, which has very flexible word order like Korean. In this paper, we proposed a statistical learning method for identification of analysis classes from requirements sentences in Korean. The approach is evaluated using the precision and recall of the automatically extracted candidate classes from real requirements sentences in Korean. The result shows that we can promise numerically measurable enhancement of performance on solving the automatic identification problem of analysis classes using statistical methods, in the real use case specifications of a banking system.