Rancang Bangun Aplikasi Peringkasan Dokumen PDF Berbasis Web Menggunakan Teknologi Natural Language Processing

Abstract

The development of artificial intelligence technology (Artificial Intelligence) especially in the field of Natural Language Processing (NLP) has made a significant contribution in the processing and analysis of digital documents. One of its applications is in the process of automatically summarizing documents that aims to help users get the gist of information from long documents more quickly and efficiently. This research aims to design and implement an artificial intelligence-based web application capable of automatically summarizing and analyzing PDF-formatted documents by utilizing the OpenRouter Application Programming Interface (API) service. The research method used is the Waterfall software development model, which covers the stages of needs analysis, system planning, implementation, testing, and maintenance. The research approach is carried out through literature studies and analysis of user needs to ensure that the developed system is able to answer existing problems. Applications are developed using MERN Stack technology which consists of MongoDB as a database, Express.js and Node.js as backend, and React.js as frontend. Integration with the OpenRouter API allows the system to leverage Transformer-based artificial intelligence models to perform natural language processing effectively. The results of this research show that the developed application is able to extract text from PDF documents, process information using NLP techniques, and produce a summary of documents that is more concise, accurate, and easy to understand by users. With this system, the document analysis process can be done more efficiently so that it helps users understand the content of the document quickly without having to read the entire content of the document.