Continuous Integration is a critical problem for software maintenance in global projects compromising companies’ performance, which tends to accumulate a high-resolution time due to the approval process, conflict resolution, tests, and validations. The process of the validation involves the commit description interpretation and can be automated by NLP-mechanisms. This paper presents an intelligent NLP-based approach to evaluate if the commits can integrate a software release based only on their descriptions, including paraphrasing. The solution is validated using pre-classified commits on the training stage and achieved an accuracy of 92.9%. The proposed solution allows the automatic integration of the commits in a release with confidence, mitigating the software managing efforts.