A Systematic Literature Review on Machine Learning for Automated Requirements Classification

被引:9
作者
Manuel Perez-Verdejo, J. [1 ]
Sanchez-Garcia, Angel J. [1 ]
Octavio Ocharan-Hernandez, Jorge [1 ]
机构
[1] Univ Veracruzana, Sch Stat & Informat, Xalapa, Veracruz, Mexico
来源
2020 8TH EDITION OF THE INTERNATIONAL CONFERENCE IN SOFTWARE ENGINEERING RESEARCH AND INNOVATION (CONISOFT 2020) | 2020年
关键词
Requirements Engineering; Requirements Classification; Machine Learning; Classification; Systematic Literature Review;
D O I
10.1109/CONISOFT50191.2020.00014
中图分类号
TP31 [计算机软件];
学科分类号
081202 ; 0835 ;
摘要
The development of quality software begins with the correct identification of the system needs. These requirements represent the basis of the subsequent activities in the software life cycle. The correct identification of these requirements in their different categories impacts on the actions taken to meet them. However, this classification can be often time-consuming or error-prone when it comes to large-scale systems, so different proposals have been made to assist in this process automatically. This systematic literature review identifies those applications of Machine Learning techniques in the classification of software requirements. In this regard, 13 articles were identified, from which relevant information on the applied algorithms, their training process, and their evaluation metrics are analyzed. From the results obtained, it is identified that the most recurrent classification algorithms featured on the identified studies are Naive Bayes, Decision Trees, and Natural Language Processing algorithms. The most frequent training datasets are academic databases and collected user reviews.
引用
收藏
页码:21 / 28
页数:8
相关论文
共 34 条
[1]   What Works Better? A Study of Classifying Requirements [J].
Abad, Zahra Shakeri Hossein ;
Karras, Oliver ;
Ghazi, Parisa ;
Glinz, Martin ;
Ruhe, Guenther ;
Schneider, Kurt .
2017 IEEE 25TH INTERNATIONAL REQUIREMENTS ENGINEERING CONFERENCE (RE), 2017, :496-501
[2]   Automatic Multi-class Non-Functional Software Requirements Classification Using Neural Networks [J].
Baker, Cody ;
Deng, Lin ;
Chakraborty, Suranjan ;
Dehlinger, Josh .
2019 IEEE 43RD ANNUAL COMPUTER SOFTWARE AND APPLICATIONS CONFERENCE (COMPSAC), VOL 2, 2019, :610-615
[3]   Automated classification of non-functional requirements [J].
Cleland-Huang, Jane ;
Settimi, Raffaella ;
Zou, Xuchang ;
Solc, Peter .
REQUIREMENTS ENGINEERING, 2007, 12 (02) :103-120
[4]  
Cleland-Huang J, 2006, RE'06: 14TH IEEE INTERNATIONAL REQUIREMENTS ENGINEERING CONFERENCE, PROCEEDINGS, P39
[5]  
Cui WW, 2010, IEEE PAC VIS SYMP, P121, DOI 10.1109/PACIFICVIS.2010.5429600
[6]   RE Data Challenge: Requirements Identification with Word2Vec and TensorFlow [J].
Dekhtyar, Alex ;
Fong, Vivian .
2017 IEEE 25TH INTERNATIONAL REQUIREMENTS ENGINEERING CONFERENCE (RE), 2017, :484-489
[7]   On non-functional requirements [J].
Glinz, Martin .
15TH IEEE INTERNATIONAL REQUIREMENTS ENGINEERING CONFERENCE, PROCEEDINGS, 2007, :21-+
[8]  
International Organization for Standardization, 2011, 25010 ISO
[9]   A Bird's Eye View on Requirements Engineering and Machine learning [J].
Iqbal, Tahira ;
Elahidoost, Parisa ;
Lucio, Levi .
2018 25TH ASIA-PACIFIC SOFTWARE ENGINEERING CONFERENCE (APSEC 2018), 2018, :11-20
[10]  
Jindal R, 2016, 2016 INTERNATIONAL CONFERENCE ON ADVANCES IN COMPUTING, COMMUNICATIONS AND INFORMATICS (ICACCI), P2027, DOI 10.1109/ICACCI.2016.7732349