View Item 
      •   IPB Repository
      • Dissertations and Theses
      • Undergraduate Theses
      • UT - School of Data Science, Mathematic and Informatics
      • UT - Computer Science
      • View Item
      •   IPB Repository
      • Dissertations and Theses
      • Undergraduate Theses
      • UT - School of Data Science, Mathematic and Informatics
      • UT - Computer Science
      • View Item
      JavaScript is disabled for your browser. Some features of this site may not work without it.

      Analisis Sentimen Terhadap Penggunaan Aplikasi Sirekap pada Pemilu 2024 Menggunakan SVM dan IndoBERTweet

      Thumbnail
      View/Open
      Cover (459.6Kb)
      Fulltext (1.928Mb)
      Lampiran (374.9Kb)
      Date
      2025
      Author
      Syafitri, Aulia Azzahra
      Agmalaro, Muhammad Asyhar
      Metadata
      Show full item record
      Abstract
      Pemilu 2024 di Indonesia memperkenalkan penggunaan aplikasi SIREKAP (Sistem Informasi Rekapitulasi) untuk meningkatkan efisiensi dan akurasi dalam perhitungan suara. Penggunaan SIREKAP ini tentunya akan menghasilkan berbagai respons dari publik, salah satunya melalui platform media sosial seperti X (Twitter). Penelitian ini bertujuan untuk melakukan analisis sentimen terhadap opini publik mengenai penggunaan aplikasi SIREKAP pada Pemilu 2024, berdasarkan data dari X. Penelitian ini juga membandingkan kinerja dua model klasifikasi sentimen: Support Vector Machine (SVM), algoritma machine learning berbasis statistika, dan IndoBERTweet, model BERT yang dilatih khusus untuk tweet berbahasa Indonesia. Data yang diperoleh merupakan data imbalance sehingga akan dilakukan SMOTE. Hasil penelitian menunjukkan bahwa IndoBERTweet secara keseluruhan memiliki kinerja yang unggul dibandingkan SVM, dengan nilai accuracy 69% dan f-1 score 68% pada model dengan data imbalance sedangkan pada model dengan SMOTE accuracy 71% dan f-1 score 70%.
       
      The 2024 General Election in Indonesia introduced the use of the SIREKAP application (Sistem Informasi Rekapitulasi or Recapitulation Information System) to improve efficiency and accuracy in vote counting. The use of SIREKAP has naturally sparked various public responses, including those expressed on social media platforms such as X (formerly Twitter). This study aims to conduct sentiment analysis on public opinions regarding the use of the SIREKAP application in the 2024 General Election, based on data collected from X. The research also compares the performance of two sentiment classification models: Support Vector Machine (SVM), a statictical based machine learning, and IndoBERTweet, a BERT model specifically trained for Indonesian social media contexts. The dataset used is imbalanced, therefore SMOTE (Synthetic Minority Oversampling Technique) is applied. The results show that IndoBERTweet outperforms SVM overall, achieving an accuracy of 69% and an F1 score of 68% on the imbalanced data model, and an accuracy of 71% and an F1 score of 70% on the SMOTE-applied model.
       
      URI
      http://repository.ipb.ac.id/handle/123456789/170111
      Collections
      • UT - Computer Science [88]

      Copyright © 2020 Library of IPB University
      All rights reserved
      Contact Us | Send Feedback
      Indonesia DSpace Group 
      IPB University Scientific Repository
      UIN Syarif Hidayatullah Institutional Repository
      Universitas Jember Digital Repository
        

       

      Browse

      All of IPB RepositoryCollectionsBy Issue DateAuthorsTitlesSubjectsThis CollectionBy Issue DateAuthorsTitlesSubjects

      My Account

      Login

      Application

      google store

      Copyright © 2020 Library of IPB University
      All rights reserved
      Contact Us | Send Feedback
      Indonesia DSpace Group 
      IPB University Scientific Repository
      UIN Syarif Hidayatullah Institutional Repository
      Universitas Jember Digital Repository