Rancang Bangun Sistem Pembuatan Surat Otomatis Berbasis Website Menggunakan Ekstraksi Informasi

Ramadani, Achmad Zaki and , Maryam S.Kom. , M.Eng (2026) Rancang Bangun Sistem Pembuatan Surat Otomatis Berbasis Website Menggunakan Ekstraksi Informasi. Skripsi thesis, Universitas Muhammadiyah Surakarta.

	PDF (Naskah Publikasi) Naskah Publikasi.pdf Download (886kB)
	PDF (Surat Pernyataan Publikasi) Surat Pernyataan Publikasi.pdf Restricted to Repository staff only Download (659kB)

Abstract

Organizations, including the Adam Malik branch of the Muhammadiyah Student Association (IMM), urgently require efficient administration, where correspondence serves as a vital communication and administrative tool. However, letter management processes that are still conducted semi-automatically or manually often lead to typographical errors and disrupt administrative workflows. This research aims to design and implement an automated letter generation system based on Natural Language Processing (NLP) using a Regular Expression (Regex) approach. The system was developed as a solution to streamline letter administration at IMM Adam Malik, which has previously been handled manually. The NLP approach is employed to identify and extract key information from narrative text inputted by users, such as event names, execution times, and venues. The successfully extracted information is then automatically integrated into official letter templates using a template-filling mechanism. This study applies the System Development Life Cycle (SDLC) method with a waterfall model, encompassing the stages of requirements analysis, system design, implementation, testing, and maintenance. Requirement analysis indicates that the system must be capable of receiving narrative or descriptive inputs, performing key information extraction using NLP models, and producing document or file outputs. The system is built using Laravel 12, Tailwind CSS (front-end), and a MySQL database. To evaluate system performance, Black Box Testing and the System Usability Scale (SUS) were utilized. Functional testing through Black Box Testing demonstrated that the system features operate according to requirements, while the System Usability Scale (SUS) evaluation yielded an average score of 79, indicating that the system falls into the "Good" category and is easily accepted by users. A comparison of two features showed that the information extraction-based feature obtained a score of 1229 (81.93%), while the form-based feature obtained a score of 1267 (84.47%), placing both in the "Excellent" category.

Item Type:	Thesis (Skripsi)
Uncontrolled Keywords:	Letter Automation, Natural Language Processing (NLP), Regular Expression (Regex), Waterfall, SDLC
Subjects:	T Technology > Technical Information T Technology > Technical Information > Software. Aplication > Software Engineering
Divisions:	Fakultas Komunikasi dan Informatika > S1 Teknik Informatika
Depositing User:	ACHMAD ZAKI RAMADANI
Date Deposited:	23 Feb 2026 06:53
Last Modified:	23 Feb 2026 06:53
URI:	http://eprints.ums.ac.id/id/eprint/143302

Actions (login required)

View Item