Software Requirements Engineering through Machine Learning Techniques: A Literature Review

In recent years, Machine Learning (AA) has shown potential for the development of better tools and software products. In relation to this situation, there are several proposals in the literature that demonstrate the application of AA techniques to address the activities and challenges that arise in Requirements Engineering (ER). This paper presents a systematic mapping of the literature in order to provide a comprehensive review of research detailing the uses and applications of AA for new perspectives and solutions to the problems present in ER. The results obtained highlight encouraging proposals mainly oriented to the prediction of failures and classification of requirements. However, they still need further empirical validation to be widely accepted and applied in software development environments. Consequently, this situation denotes the need to continue researching and deepening the possible applications of AA techniques in the area of ER.