PENERAPAN SUPPORT VECTOR MACHINE UNTUK MENGANALISIS SENTIMEN MASYARAKAT TERHADAP PROGRAM MAGANG DAN STUDI INDEPENDEN BERSERTIFIKAT

ERSTYNA KATHLYA PRABOWO, . (2023) PENERAPAN SUPPORT VECTOR MACHINE UNTUK MENGANALISIS SENTIMEN MASYARAKAT TERHADAP PROGRAM MAGANG DAN STUDI INDEPENDEN BERSERTIFIKAT. Sarjana thesis, UNIVERSITAS NEGERI JAKARTA.

[img] Text
COVER.pdf

Download (3MB)
[img] Text
BAB 1.pdf

Download (1MB)
[img] Text
BAB 2.pdf
Restricted to Registered users only

Download (3MB) | Request a copy
[img] Text
BAB 3.pdf
Restricted to Registered users only

Download (727kB) | Request a copy
[img] Text
BAB 4.pdf
Restricted to Registered users only

Download (3MB) | Request a copy
[img] Text
BAB 5.pdf
Restricted to Registered users only

Download (505kB) | Request a copy
[img] Text
DAFTAR PUSTAKA.pdf

Download (1MB)
[img] Text
LAMPIRAN.pdf
Restricted to Registered users only

Download (1MB) | Request a copy

Abstract

Program Magang dan Studi Independen Bersertifikat (MSIB) merupakan salah satu program yang dicetuskan oleh Kemendikbud untuk mendukung salah satu kebijakan kurikulum Kampus Merdeka yang memberikan hak kepada mahasiswa untuk belajar di luar kampus selama tiga semester. Selama berjalan hampir dua tahun, pro�gram MSIB menuai opini dan pendapat dari masyarakat terhadap program ini, baik yang mengandung sentimen negatif, positif, atau netral. Penelitian ini bertujuan un�tuk menganalisis sentimen masyarakat terhadap program MSIB menggunakan Support Vector Machine (SVM). Support Vector Machine merupakan model machine learning yang dapat bekerja dengan baik pada data berdimensi tinggi seperti data teks. Hasil penelitian menunjukkan bahwa rata-rata F1 score yang dihasilkan oleh Support Vector Machine pada saat tahap 5-Fold Cross Validation adalah sebesar 68,2%. Kinerja Support Vector Machine dalam mengklasifikasikan data baru termasuk pada kriteria cukup baik, yaitu menghasilkan nilai F1 score sebesar 74,12% ketika digunakan untuk mengklasifikasikan sentimen pada data uji. Hasil keseluruhan klasifikasi sentimen menggunakan Support Vector Machine menunjukkan bahwa sentimen netral menjadi kelas sentimen paling dominan dalam pendapat dan opini masyarakat terhadap program MSIB (74,39%), sedangkan sentimen negatif menjadi kelas sentimen kedua yang frekuensinya paling banyak muncul (13,60%). Sentimen positif menjadi kelas sentimen yang paling sedikit muncul pada pendapat dan opini masyarakat terhadap program MSIB (12%). Sentimen netral men�dominasi pendapat dan opini masyarakat terhadap program MSIB terjadi karena banyaknya data opini yang cenderung merupakan kalimat pertanyaan atau kalimat berita tentang program MSIB itu sendiri. **** Certified Internship and Independent Study Program (MSIB) is one of the programs which initiated by the Ministry of Education, Culture, Research and Technology to support one of the Kampus Merdeka curriculum policies that give opportunities for students to learn and develop themselves through activities outside class for three semesters. After almost two years, the MSIB program has received opinions from the public, whether it contains negative, positive, or neutral sentiments. This research aims to analyze public sentiment towards the MSIB program using Support Vector Machine (SVM). Support Vector Machine is a machine learning model that can work well on high-dimensional data, such as text data. The result shows that the average F1 score given by the Support Vector Machine when passed the 5-Fold Cross Validation process is 68,2%. The performance of the Support Vector Machine in classifying new data is categorized as tolerable, which produced an F1 Score of 74,12%, when using SVM to classify sentiments on data test. The overall results of sentiment classification using the Support Vector Machine show that neutral sentiment dominates public opinion about the MSIB program (74,39%), while negative sentiment becomes the second class of sentiment with the highest frequency (13,60%). Positive sentiment is the class sentiment that appears the least in public opinions about the MSIB program (12%). Neutral sentiment dominates public opinion toward the MSIB program because a large amount of opinion data contains interrogative sentences or news about the MSIB program itself.

Item Type: Thesis (Sarjana)
Additional Information: 1). Dr. Dian Handayani, M.Si. ; 2). Devi Eka Wardani Meganingtyas, S.Pd., M.Si.
Subjects: Sains > Matematika
Divisions: FMIPA > S1 Matematika
Depositing User: Users 18969 not found.
Date Deposited: 06 Sep 2023 01:04
Last Modified: 06 Sep 2023 01:04
URI: http://repository.unj.ac.id/id/eprint/40302

Actions (login required)

View Item View Item