Integration of Natural Language Processing in a Web-Based Translanguaging System for Arabic-Indonesian Language Learning

Abstract

Arabic–Indonesian language learners often face challenges in understanding the contextual meaning of texts due to differences in morphological and syntactic structures between the two languages. To address this, this study proposes the development of a web-based translanguaging system integrated with Natural Language Processing (NLP) to help users understand and translate texts more meaningfully. This system was developed using the Waterfall model with stages of requirements analysis, design, implementation, testing, and maintenance. The implemented NLP module includes tokenization, part-of-speech tagging, and sentence structure analysis to produce translations that consider context, not just literal word equivalents. The implementation results show that the system is able to improve user comprehension of Arabic–Indonesian texts with a simple and accessible interface. Furthermore, the translation history feature supports continuous self-learning. Although the system still has limitations in handling idiomatic text and complex sentence structures, the NLP integration has proven effective in improving the quality of translanguaging. This research contributes to the development of bilingual learning technology and can be further developed using deep learning models such as BERT or mBERT to improve semantic and contextual accuracy.