View Item 
      •   IPB Repository
      • Dissertations and Theses
      • Undergraduate Theses
      • UT - Faculty of Mathematics and Natural Sciences
      • UT - Statistics and Data Sciences
      • View Item
      •   IPB Repository
      • Dissertations and Theses
      • Undergraduate Theses
      • UT - Faculty of Mathematics and Natural Sciences
      • UT - Statistics and Data Sciences
      • View Item
      JavaScript is disabled for your browser. Some features of this site may not work without it.

      Penerapan Support Vector Machine untuk Analisis Sentimen Ulasan Aplikasi LinkedIn

      Thumbnail
      View/Open
      Cover (582.1Kb)
      Fullteks (1.120Mb)
      Lampiran (138.4Kb)
      Date
      2024
      Author
      Imani, Diftania Putri
      Rizki, Akbar
      Alamudi, Aam
      Metadata
      Show full item record
      Abstract
      LinkedIn adalah aplikasi yang digunakan untuk membantu individu membangun jaringan dan menemukan peluang karir dengan lebih dari 722 juta pengguna di seluruh dunia. Popularitas aplikasi LinkedIn yang tinggi juga diiringi oleh tuntutan akan layanan aplikasi yang berkualitas tinggi. Hal tersebut ditunjukkan pada ulasan pengguna di Google Play Store. Penelitian ini mengidentifikasi sentimen ulasan pengguna aplikasi di Google Play Store yang diklasifikasikan menjadi opini positif dan negatif menggunakan algoritma Support Vector Machine (SVM). Data yang digunakan dalam penelitian ini adalah data ulasan aplikasi LinkedIn berbahasa Inggris di Google Play Store sejak tanggal 22 Februari 2023 hingga 22 Maret 2023. Mayoritas ulasan sentimen positif menunjukkan bahwa aplikasi LinkedIn memberikan layanan sesuai yang dijanjikan, yaitu membantu memperluas jaringan professional. Mayoritas ulasan sentimen negatif menyebutkan keluhan pada aplikasi, seperti gagal membayar premi, tidak bisa login, dan kendala pembaruan aplikasi. Pemodelan SVM menggunakan kernel linier menghasilkan kinerja yang cukup baik dalam mengklasifikasikan sentimen, dengan nilai rata-rata akurasi, sensitivitas, dan spesifisitas dengan 10-fold cross-validation sebesar 95,6%, 96,7%, dan 92%. Nilai akurasi menyatakan bahwa 95,6% prediksi klasifikasi kelas sentimen sesuai dengan kelas sentimen sebenarnya.
       
      LinkedIn is an application used to help individuals build networks and find career opportunities. LinkedIn is the world's largest professional network, with over 722 million global users. The high popularity of the LinkedIn app is also accompanied by a demand for high quality app services. This is reflected in user reviews on the Google Play Store. This research identifies the sentiment of application user reviews on the Google Play Store which are classified into positive and negative opinions using the Support Vector Machine (SVM) algorithm. The data used in this study is the English-language LinkedIn application review data on the Google Play Store from February 22, 2023 to March 22, 2023. The majority of positive sentiment reviews indicate that the LinkedIn application provides the promised service, which helps expand the professional network. The majority of negative sentiment reviews mentioned complaints about the application, such as failing to pay premiums, not being able to log in, and application update problems. SVM modeling using a linear kernel resulted in a fairly good performance in classifying sentiment, with average values of accuracy, sensitivity, and specificity with 10-fold cross-validation of 95.6%, 96.7%, and 92%. The accuracy value states that 95.6% of the predicted sentiment class classification matches the actual sentiment class.
       
      URI
      http://repository.ipb.ac.id/handle/123456789/152907
      Collections
      • UT - Statistics and Data Sciences [2260]

      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