• Login
    View Item 
    •   USU-IR Home
    • Faculty of Computer Science and Information Technology
    • Department of Information Technology
    • Undergraduate Theses
    • View Item
    •   USU-IR Home
    • Faculty of Computer Science and Information Technology
    • Department of Information Technology
    • Undergraduate Theses
    • View Item
    JavaScript is disabled for your browser. Some features of this site may not work without it.

    Analisis Sentimen pada Kepuasan Pelayanan E-Commerce Menggunakan Lexicon Based Features dan Support Vector Machine

    View/Open
    Fulltext (1.976Mb)
    Date
    2021
    Author
    Wulandari, Diana
    Advisor(s)
    Siregar, Baihaqi
    Jaya, Ivan
    Metadata
    Show full item record
    Abstract
    Review pada e-commerce dapat membantu calon pembeli untuk membeli suatu produk, keputusan apakah produk yang ingin dibeli baik atau buruk dan dapat membantu penjual untuk mendapatkan feedback dari konsumen. Namun, ada dua masalah yang muncul, jumlah review produk yang semakin hari semakin meningkat dan e-commerce memungkinkan konsumennya untuk menulis opini negatif positif dari beberapa fitur produk dalam satu review, yang disebut sebagai "format bebas". Oleh karena itu, diperlukan suatu pendekatan dengan mengimplementasikan logika fuzzy dan cosinus similarity yang dapat mengekstrak fitur produk dari ulasan dan mengklasifikasikan ulasan ke dalam kategori yang berbeda. Metode svm dan leksikon dapat diimplementasikan dalam ekstraksi ciri produk. Skor F terbaik dari analisis sentimen ini menghasilkan presisi 78% dan recall 84% dan skor f1 menghasilkan 79%.
     
    Reviews on e-commerce can help potential buyers to buy a product,the decision whether the product they want to buy is good or bad and it can help sellers to get feedback from consumers. However, there are two problems that arise, the number of product reviews is increasing day by day and e-commerce allows their consumers to write positive negative opinions of several product features in one review, which is referred to as "free format". Therefore, an approach is needed by implementing fuzzy logic and cosine similarity that can extract product features from reviews and classify reviews into different categories. Svm and lexicon methods can be implemented in product feature extraction. The best F score from this sentiment analysis is to produce 78% precision and 84% recall and f1 score to produce 79%.

    URI
    https://repositori.usu.ac.id/handle/123456789/46713
    Collections
    • Undergraduate Theses [797]

    Repositori Institusi Universitas Sumatera Utara (RI-USU)
    Universitas Sumatera Utara | Perpustakaan | Resource Guide | Katalog Perpustakaan
    DSpace software copyright © 2002-2016  DuraSpace
    Contact Us | Send Feedback
    Theme by 
    Atmire NV
     

     

    Browse

    All of USU-IRCommunities & CollectionsBy Issue DateTitlesAuthorsAdvisorsKeywordsTypesBy Submit DateThis CollectionBy Issue DateTitlesAuthorsAdvisorsKeywordsTypesBy Submit Date

    My Account

    LoginRegister

    Repositori Institusi Universitas Sumatera Utara (RI-USU)
    Universitas Sumatera Utara | Perpustakaan | Resource Guide | Katalog Perpustakaan
    DSpace software copyright © 2002-2016  DuraSpace
    Contact Us | Send Feedback
    Theme by 
    Atmire NV