Using Machine Learning to Design a Flexible LOC Counter

Ochodek, Miroslaw, 1980 (author): Politechnika Poznanska,Poznan University of Technology

Staron, Miroslaw, 1977 (author): Gothenburg University,Göteborgs universitet,Institutionen för data- och informationsteknik (GU),Institutionen för data- och informationsteknik, Software Engineering (GU),Department of Computer Science and Engineering (GU),Institutionen för data- och informationsteknik, Software Engineering (GU),University of Gothenburg

Bargowski, Dominik, 1990 (author): Politechnika Poznanska,Poznan University of Technology

Hebig, Regina (author): Gothenburg University,Göteborgs universitet,Institutionen för data- och informationsteknik, Software Engineering (GU),Institutionen för data- och informationsteknik (GU),Institutionen för data- och informationsteknik, Software Engineering (GU),Department of Computer Science and Engineering (GU),University of Gothenburg

(creator_code:org_t)

IEEE, 2017
2017
English.
In: Workshop on Machine Learning Techniques for Software Quality Evaluation. - : IEEE. - 9781509065974

Related links:: https://gup.ub.gu.se... (primary) (free); show more...; https://gup.ub.gu.se...; https://doi.org/10.1...; https://research.cha...; show less...

Abstract Subject headings

Abstract—Background: The results of counting the size of programs in terms of Lines-of-Code (LOC) depends on the rules used for counting (i.e. definition of which lines should be counted). In the majority of the measurement tools, the rules are statically coded in the tool and the users of the measurement tools do not know which lines were counted and which were not. Goal: The goal of our research is to investigate how to use machine learning to teach a measurement tool which lines should be counted and which should not. Our interest is to identify which parameters of the learning algorithm can be used to classify lines to be counted. Method: Our research is based on the design science research methodology where we construct a measurement tool based on machine learning and evaluate it based on open source programs. As a training set, we use industry professionals to classify which lines should be counted. Results: The results show that classifying the lines as to be counted or not has an average accuracy varying between 0.90 and 0.99 measured as Matthew’s Correlation Coefficient and between 95% and nearly 100% measured as the percentage of correctly classified lines. Conclusions: Based on the results we conclude that using machine learning algorithms as the core of modern measurement instruments has a large potential and should be explored further.

By the author/editor: Ochodek, Mirosla ...; Staron, Miroslaw ...; Bargowski, Domin ...; Meding, Wilhelm, ...; Hebig, Regina

About the subject

NATURAL SCIENCES: NATURAL SCIENCES; and Computer and Inf ...; and Software Enginee ...

NATURAL SCIENCES: NATURAL SCIENCES; and Computer and Inf ...; and Language Technol ...

By the university: University of Gothenburg; Chalmers University of Technology

Kungliga biblioteket hanterar dina personuppgifter i enlighet med EU:s dataskyddsförordning (2018), GDPR. Läs mer om hur det funkar här.
Så här hanterar KB dina uppgifter vid användning av denna tjänst.