Abstract Nowadays, there is a lack of guidelines in computing curriculums in Peru. Most of them do not follow the ACM/IEEE international standards. Also, accreditation of computing programs is a time-consuming and manual task. In order to tackle these issues, we propose an automatic process to identify a curriculum according to ACM/IEEE standards. Our initial solution combines word embedding and visualization techniques. Our results confirm disorder and confusing in Peruvian curriculums. For future work, we plan to collect more data and try more elaborate techniques such as metric learning and recurrent neural networks.