<![CDATA[The challenge in the education domain is ensuring that learning can be evaluated effectively and in a structured manner to improve and strengthen the quality of education standards in achieving optimal learning. In this study, an implementation was carried out to evaluate learning outcomes based on Natural Language Processing using BERT (IndoBERT) and Cosine similarity to assess the consistency and accuracy of learning materials with BAKP and RPS. IndoBERT is used to extract embedding vectors as contextual semantic representations from documents, and the similarity level is calculated using Cosine Similarity between the contents of BAKP and RPS to ensure the achievement of learning objectives. The research methodology consists of data collection, pre-processing, tokenization, and sentence embedding using IndoBERT, calculating the similarity level, and evaluating model performance. The results showed that implementing the IndoBERT model produced a good level of similarity with a value above the threshold, which was 0.50, with a Cosine Similarity result of 0.674 and a performance evaluation of 100%. This approach can provide the potential for automation of the higher education quality assurance process for academic evaluation based on BAKP and RPS so that learning materials are always relevant and updated with industry needs.]]>
Copyrights © 2025
