ML@SE: What do we know about how Machine Learning impact Software Engineering practice?

Autor(es)

Borges, Olimar ; Lima, Marcia ; Couto, Julia ; Gadelha, Bruno ; Conte, Tayana ; Prikladnicki, Rafael ; Rocha, A ; Bordel, B ; Penalvo, FG ; Goncalves, R

• Tipo de documento: Artigo Científico
• Fonte: 2022 17TH IBERIAN CONFERENCE ON INFORMATION SYSTEMS AND TECHNOLOGIES (CISTI); v. N/A, p. 6-pg., 2022-01-01.

Resumo

Machine learning (ML) based approaches provide efficient solutions successfully applied to different domains. In Software Engineering (SE) domain, ML is improving and automating various development activities, such as requirement classification, refactoring, defects prediction, and effort estimation. We investigated whether and how ML techniques currently support software development tasks and improve the way practitioners do their job. To achieve this objective, we performed a literature review and snowballing, obtaining a set of 209 articles. As a result, we present an organized approach among the first ten areas of SWEBOK, which guides possible ML solutions used in the tasks of the SE. (AU)

• Processo FAPESP: 20/05191-2 - INDEXAR: INDividualização da EXperiência de uso em ferramentas de apoio à Aprendizagem Remota
• Beneficiário: Tayana Uchôa Conte
• Modalidade de apoio: Auxílio à Pesquisa - Regular