UI - Skripsi Membership :: Back

UI - Skripsi Membership :: Back

Pengembangan Sistem Penilaian Esai Otomatis (SIMPLE-O) untuk Ujian Bahasa Jepang dengan Klasifikasi Support Vector Machine (SVM) dan Metode Latent Semantic Analysis (LSA) = Development of Automated Essay Grading (SIMPLE-O) for Japanese Examination Using Support Vector Machine (SVM) Classification and Latent Semantic Analysis (LSA) Method

Aaliyah Kaltsum; Anak Agung Ayu Ratna Dewi, supervisor; Prima Dewi Purnamasari, examiner; Diyanatul Husna, examiner (Fakultas Teknik Universitas Indonesia, 2019)

 Abstract

ABSTRAK
Pada penelitian ini dilakukan penerapan Support Vector Machine dan LSA
Metode tersebut dibahas dan dipelajari lebih lanjut untuk merancang Sistem Penilaian Esai Otomatis (Simple-O). Simple-O merupakan sistem yang saat ini dikembangkan oleh UI Jurusan Teknik Elektro yang bertujuan untuk menilai esai secara otomatis. Support Vector Machine, yang merupakan algoritma pembelajaran yang diawasi, dipelajari selanjutnya untuk meningkatkan tingkat akurasi dalam Simple-O bersama dengan metode LSA yang digunakan Bahasa pemrograman Python. Dari hasil tes rata-rata tertinggi skor akurasi yang diperoleh sistem sebesar 88.06% dengan masukan kalimat kanji, katakana, hiragana dan nilai TDM siswa jawaban yang mencerminkan frekuensi kemunculan kata kunci dalam dokumen.

ABSTRACT
In this study, the implementation of Support Vector Machine and LSA was carried out These methods are discussed and studied further to design an Essay Assessment System Automatic (Simple-O). Simple-O is a system currently being developed by the UI Department of Electrical Engineering which aims to assess essays automatically. Support Vector Machine, which is a supervised learning algorithm, is learned furthermore to increase the level of accuracy in Simple-O along with the LSA method used Python programming language. From the highest average test results the accuracy score obtained by the system is 88.06% with input the kanji, katakana, hiragana and TDM scores of the students answers that reflect the frequency with which keywords appear in the document.

 Digital Files: 1

Shelf
 S-Aaliyah Kaltsum.pdf :: Download

LOGIN required

 Metadata

Collection Type : UI - Skripsi Membership
Call Number : S-pdf
Main entry-Personal name :
Additional entry-Personal name :
Additional entry-Corporate name :
Study Program :
Subject :
Publishing : Depok: Fakultas Teknik Universitas Indonesia, 2019
Cataloguing Source LibUI ind rda
Content Type text
Media Type computer
Carrier Type online resource
Physical Description xvii, 84 pages ; 30 cm
Concise Text
Holding Institution Universitas Indonesia
Location Perpustakaan UI. Lantai 3
  • Availability
  • Review
  • Cover
Call Number Barcode Number Availability
S-pdf 14-22-35554797 TERSEDIA
Review:
No review available for this collection: 20489247
Cover