<![CDATA[This research aims to examine and implement text analysis of social assistance recipients data using Natural Language Processing (NLP) methods as a solution to accelerate and improve efficiency in the process of categorizing aid recipients. Based on the design and testing processes carried out, the developed system is capable of automatically processing descriptive data of aid recipients and grouping them into appropriate categories, such as the elderly, school children, pregnant women, the disabled, and minors. The research design uses System Development Research. The results of the NLP system implementation in the case study of categorizing social assistance recipients in Girisubo District show a significant improvement in operational efficiency and classification accuracy. Quantitatively, the trained NLP model successfully achieved high performance metrics. The average classification accuracy exceeds 90%, with data clustering computation time much faster compared to the manual process that takes hours. The main conclusion of this study indicates that the implementation of Natural Language Processing (NLP) in Girisubo District is effective in classifying categories of aid recipients. The model shows the strongest performance in the Pregnant Women group (95% Accuracy) and Persons with Disabilities (97% Accuracy) with perfect Precision of 100%. The performance for the Elderly and School Children is also very good (minimum 89% Accuracy). Overall, the system has proven reliable and is capable of automatically grouping descriptive data into the appropriate categories.]]>
Copyrights © 2026
