Klasifikasi Emosi Komentar Youtube Program Makan Bergizi Gratis Menggunakan Algoritma SVM Dan Logistic Regression

Artanti, Karina Dinda (2026) Klasifikasi Emosi Komentar Youtube Program Makan Bergizi Gratis Menggunakan Algoritma SVM Dan Logistic Regression. Undergraduate thesis, UPN Veteran Jawa Timur.

[img] Text (Cover)
Cover.pdf
Download (903kB)
[img] Text (BAB I)
BAB 1.pdf
Download (291kB)
[img] Text (BAB II)
BAB 2.pdf
Restricted to Repository staff only until 17 July 2029.
Download (494kB)
[img] Text (BAB III)
BAB 3.pdf
Restricted to Repository staff only until 20 July 2029.
Download (545kB)
[img] Text (BAB IV)
BAB 4.pdf
Restricted to Repository staff only until 20 July 2029.
Download (735kB)
[img] Text (BAB V)
BAB 5.pdf
Download (262kB)
[img] Text (DAFTAR PUSTAKA)
DAFTAR PUSTAKA.pdf
Download (186kB)
[img] Text (LAMPIRAN)
LAMPIRAN.pdf
Restricted to Repository staff only until 20 July 2029.
Download (427kB)

Abstract

Public comments on YouTube contain valuable insights for evaluating public response to government policies but are difficult to analyze manually. This study classifies the emotions of YouTube comments regarding the Program Makan Bergizi Gratis (MBG) into eight Plutchik emotion classes using Support Vector Machine (SVM) and Logistic Regression (LR) algorithms. A total of 13,840 valid comments (from 17,959 scraped through the YouTube Data API v3) were labeled using the Indonesian NRC Emotion Lexicon and evaluated across six scenarios combining the algorithms with TF-IDF, Bag of Words, and Word2Vec on an 80:20 split. The combination of Logistic Regression and Bag of Words achieved the best performance, and after hyperparameter tuning with GridSearchCV (C = 10) reached an accuracy of 86.24% and a weighted F1-score of 86.09%. A generalization test on 267 new MBG comments produced an accuracy of 80.86%. The best model was deployed as a web application named EmotiSense MBG using the Flask framework.

Item Type: Thesis (Undergraduate)
Contributors:
ContributionContributorsNIDN/NIDKEmail
Thesis advisorWati, Seftin Fitri AnaNIDN0020039104seftin.fitri.si@upnjatim.ac.id
Thesis advisorNajaf, Abdul Rezha EfratNIDN0029099403rezha.efrat.sifo@upnjatim.ac.id
Subjects: T Technology > T Technology (General) > T58.6-58.62 Management Information Systems
Divisions: Faculty of Computer Science > Departemen of Information Systems
Depositing User: Karina Dinda Artanti
Date Deposited: 21 Jul 2026 02:53
Last Modified: 21 Jul 2026 06:09
URI: https://repository.upnjatim.ac.id/id/eprint/55885

Actions (login required)

View Item View Item