Institutional Repository
| an empirical study on classification of non-functional requirements | |
| Zhang Wen; Yang Ye; Wang Qing; Shu Fengdi | |
| 2011 | |
| Conference Name | SEKE 2011 - Proceedings of the 23rd International Conference on Software Engineering and Knowledge Engineering |
| Source | SEKE 2011 - Proceedings of the 23rd International Conference on Software Engineering and Knowledge Engineering |
| Pages | 444-449 |
| Conference Date | July 7, 20 |
| Conference Place | Miami, FL, United states |
| Indexed Type | EI |
| ISBN | 1891706292 |
| Department | (1) Laboratory for Internet Software Technologies Institute of Software Chinese Academy of Sciences Beijing 100190 China |
| English Abstract | The classification of NKRs brings about the benefits that NKRs with respect to the same type In the system can be considered and Implemented aggregately by developers, and as a result be verified by quality assurers assigned for the type. This paper conducts an empirical study on using text mining techniques to classify NFRs automatically. Three kinds of Index terms, which are at different levels of llngulstlcal semantics, as Vgrams. Individual words, and multi-word expressions (MWE), are used In representation of NFRs. Then. SVM (Support Vector Machine) with linear kernel bt used as the classifier. We collected a data set from PROMISE web site for experimentation In this empirical study. The experiments show that Index term as Individual words with Boolean weighting outperforms the other two Index terms. When MWEs are used to enhance representation of Individual words, there Is no significant Improvement on classification performance. Automatic classification produces better performance on categories of large stees than that on categories of small sizes. It can be drawn from the experimental results that for automatic classification of NFRs. Individual words are the best Index terms In text representation of short NFRs' description and we should collect as many as possible NFRs of software system.; The classification of NKRs brings about the benefits that NKRs with respect to the same type In the system can be considered and Implemented aggregately by developers, and as a result be verified by quality assurers assigned for the type. This paper conducts an empirical study on using text mining techniques to classify NFRs automatically. Three kinds of Index terms, which are at different levels of llngulstlcal semantics, as Vgrams. Individual words, and multi-word expressions (MWE), are used In representation of NFRs. Then. SVM (Support Vector Machine) with linear kernel bt used as the classifier. We collected a data set from PROMISE web site for experimentation In this empirical study. The experiments show that Index term as Individual words with Boolean weighting outperforms the other two Index terms. When MWEs are used to enhance representation of Individual words, there Is no significant Improvement on classification performance. Automatic classification produces better performance on categories of large stees than that on categories of small sizes. It can be drawn from the experimental results that for automatic classification of NFRs. Individual words are the best Index terms In text representation of short NFRs' description and we should collect as many as possible NFRs of software system. |
| Keyword | Experiments Knowledge Engineering Semantics Support Vector Machines |
| Sponsorship | Knowledge Systems Institute Graduate School |
| Language | 英语 |
| Content Type | 会议论文 |
| URI | http://ir.iscas.ac.cn/handle/311060/16268 |
| Collection | 中国科学院软件研究所 |
| Recommended Citation GB/T 7714 | Zhang Wen,Yang Ye,Wang Qing,et al. an empirical study on classification of non-functional requirements[C],2011:444-449. |
| Files in This Item: | There are no files associated with this item. | |||||
Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.
Edit Comment