RT info:eu-repo/semantics/article
T1 Software Design Smell Detection: a systematic mapping study
A1 Alkharabsheh, Khalid
A1 Crespo, Yania
A1 Manso, M. Esperanza
A1 Taboada, José A.
K1 DesignSmell . Antipatterns. Detection tools. Quality models. Systematic mapping study
AB Design Smells are indicators of situations that negatively affect software quality attributes suchas understandability, testability, extensibility, reusability, and maintainability in general. Improving maintainability is one of the cornerstones of making software evolution easier. Hence,Design Smell Detection is important in helping developers when making decisions that canimprove software evolution processes. After a long period of research, it is important toorganize the knowledge produced so far and to identify current challenges and future trends.In this paper, we analyze 18 years of research into Design Smell Detection. There is a widevariety of terms that have been used in the literature to describe concepts which are similar towhat we have defined as “Design Smells,” such as design defect, design flaw, anomaly, pitfall,antipattern, and disharmony. The aim of this paper is to analyze all these terms and includethem in the study. We have used the standard systematic literature review method based on acomprehensive set of 395 articles published in different proceedings, journals, and bookchapters. We present the results in different dimensions of Design Smell Detection, such asthe type or scope of smell, detection approaches, tools, applied techniques, validation evidence, type of artifact in which the smell is detected, resources used in evaluation, supportedlanguages, and relation between detected smells and software quality attributes according to aquality model. The main contributions of this paper are, on the one hand, the application ofdomain modeling techniques to obtain a conceptual model that allows the organization of theknowledge on Design Smell Detection and a collaborative web application built on thatknowledge and, on the other, finding how tendencies have moved across different kinds ofsmell detection, as well as different approaches and techniques. Key findings for future trendsinclude the fact that all automatic detection tools described in the literature identify DesignSmells as a binary decision (having the smell or not), which is an opportunity to evolve tofuzzy and prioritized decisions. We also find that there is a lack of human experts andbenchmark validation processes, as well as demonstrating that Design Smell Detectionpositively influences quality attributes.
PB Springer Nature
SN 0963-9314
YR 2019
FD 2019
LK https://uvadoc.uva.es/handle/10324/74617
UL https://uvadoc.uva.es/handle/10324/74617
LA eng
NO Software Quality Journal 27, 1069–1148 (2019)
NO Producción Científica
DS UVaDOC
RD 31-ene-2025