• 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.

    Deteksi Judul Berita Clickbait Bahasa Indonesia Menggunakan Convolutional Neural Network (CNN)

    View/Open
    Fulltext (1.958Mb)
    Date
    2021
    Author
    Sinamo, Pratiwi Rohnola Restu
    Advisor(s)
    Aulia, Indra
    Gunawan, Dani
    Metadata
    Show full item record
    Abstract
    Online medias are one of the developments in internet technology and information providers that can be accessed by almost all people in Indonesia. According to the results by the Indonesian Internet Service Providers Association (APJII), the growth of internet users in Indonesia in the period 2019-2020 amounted to 196,71 million people out of a total population of 266,91 million Indonesians. The growing population of online news portals in Indonesia has made competition for the online news portal industry to be fierce. Online media also tries to attract the attention of readers by presenting information that is able to answer the needs and attract the attention of the audience. Clickbait is an online media trick to increase visitors, traffic and pageviews. Clickbait can become fake news or hoaxes. This study use a dataset of Indonesian clickbait news titles from several online news portals in Indonesia to identify Indonesian clickbait news titles automatically. This study apply one of the Neural Network methods, namely Convolutional Neural Network. This study provides about 72,3% accuracy and the resulting model can identify clickbait or non-clickbait headlines.
     
    Media online merupakan salah satu perkembangan teknologi internet dan penyedia informasi yang dapat diakses oleh hampir seluruh masyarakat Indonesia. Dari hasil survei Asosiasi Penyedia Jasa Internet Indonesia (APJII), pertumbuhan pengguna internet di Indonesia dalam kurun waktu 2019-2020 berjumlah 196,71 juta jiwa dari populasi penduduk Indonesia 266,91 juta jiwa. Pertumbuhan media online di Indonesia membuat persaingan industri media online semakin kompetitif. Media online juga berusaha menarik perhatian pembaca dengan memberikan informasi yang dapat menjawab kebutuhan dan menarik perhatian audiens. Pancingan klik (clickbait) merupakan cara yang digunakan oleh media online dalam menaikkan jumlah pengunjung, traffic dan pageviews. Clickbait berpotensi menjadi berita bohong atau hoax. Penelitian ini menggunakan sebuah dataset judul berita clickbait bahasa Indonesia dari beberapa portal berita online di Indonesia untuk mengidentifikasi judul berita clickbait bahasa Indonesia secara otomatis. Penelitian ini menerapkan salah satu metode Jaringan Saraf Tiruan, yaitu Convolutional Neural Network. Penelitian ini memberikan akurasi sekitar 72,3% dan model yang dihasilkan dapat melakukan identifikasi judul berita clickbait atau non-clickbait.

    URI
    http://repositori.usu.ac.id/handle/123456789/43078
    Collections
    • Undergraduate Theses [800]

    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