View Item 
      •   IPB Repository
      • Dissertations and Theses
      • Undergraduate Theses
      • UT - Vocational School
      • UT - Software Engineering Technology
      • View Item
      •   IPB Repository
      • Dissertations and Theses
      • Undergraduate Theses
      • UT - Vocational School
      • UT - Software Engineering Technology
      • View Item
      JavaScript is disabled for your browser. Some features of this site may not work without it.

      Perancangan Fitur Interaktif pada Halaman Detail Berita Berbasis Website di iNews menggunakan Metode Prototype Model

      Thumbnail
      View/Open
      Cover (2.276Mb)
      Fulltext (2.979Mb)
      Lampiran (3.089Mb)
      Date
      2025
      Author
      Zafira, Cut Yasmin
      Aziezah, Nur
      Metadata
      Show full item record
      Abstract
      iNews merupakan portal berita digital yang menyediakan informasi dari berbagai kategori dan saat ini sedang menghadapi tantangan berupa bounce rate yang tinggi, yakni di atas 70%, yang menunjukkan rendahnya keterlibatan pengguna. Penelitian ini bertujuan untuk mengembangkan dua fitur interaktif, yaitu Breaking News Related dan Related Polling, untuk meningkatkan keterlibatan pengguna. Pengembangan dilakukan menggunakan metode Prototype Model untuk memastikan fitur sesuai dengan kebutuhan pengguna. Fitur dirancang menggunakan Figma dan diimplementasikan dengan teknologi Vue.js, Express.js, Node.js, dan MySQL. Evaluasi dilakukan melalui metode A/B Testing, yang menunjukkan rata-rata interaksi pengguna melebihi 90%. Selanjutnya, efektivitas fitur dievaluasi menggunakan model klasifikasi ensemble yang menggabungkan XGBoost, Random Forest, dan Logistic Regression. Model ini menunjukkan akurasi prediksi sebesar 67,7%, dengan precision dan recall rata-rata sebesar 68%. Fitur yang dikembangkan terbukti dapat menjadi solusi dalam meningkatkan keterlibatan pengguna dan berpotensi menurunkan bounce rate pada halaman detail artikel iNews.
       
      iNews is a digital news portal that provides information across various categories and is currently facing a major challenge in the form of a high bounce rate, which exceeds 70%, indicating low user engagement. This study aims to develop two interactive features, namely Breaking News Related and Related Polling, to enhance user engagement. The development process adopted the Prototype Model method to ensure that the features align with user needs. The features were designed using Figma and implemented with Vue.js, Express.js, Node.js, and MySQL. Evaluation was conducted through the A/B Testing method, which showed that average user interaction exceeded 90%. Furthermore, the effectiveness of the features was evaluated using an ensemble classification model combining XGBoost, Random Forest, and Logistic Regression. The model achieved a prediction accuracy of 67.7%, with average precision and recall values of 68%. The developed features have proven to be a potential solution for increasing user engagement and reducing bounce rates on the iNews article detail pages.
       
      URI
      http://repository.ipb.ac.id/handle/123456789/169591
      Collections
      • UT - Software Engineering Technology [182]

      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