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

      Analisis Data Publikasi Dengan Pendekatan Bibliometriks dan Text Clustering Untuk Menentukan Kriteria Tingkat Keparahan Karhutla

      Thumbnail
      View/Open
      Cover (769.5Kb)
      Fulltext (1.543Mb)
      Lampiran (726.5Kb)
      Date
      2024
      Author
      Widiyarto, Muhammad Iqbal Alvian
      Adrianto, Hari Agung
      Sitanggang, Imas Sukaesih
      Metadata
      Show full item record
      Abstract
      Kebakaran hutan dan lahan (karhutla) di Indonesia telah menjadi isu lingkungan selama dua dekade terakhir, dengan dampaknya yang melibatkan berbagai aspek. Penilaian dampak kebakaran terutama dilakukan untuk penelitian, perencanaan rehabilitasi hutan, konservasi, dan penegakan hukum. Namun, standar penilaian dampak kebakaran yang digunakan sebagai acuan pengendalian karhutla masih sangat beragam. Penelitian ini bertujuan untuk mengidentifikasi kriteria untuk mengukur tingkat keparahan kebakaran hutan dengan menerapkan algoritma Bibliometriks dan text mining. Selain itu, analisis bibliometriks akan dibandingkan dengan hasil dari analisis clustering. Penelitian ini membandingkan beberapa algoritma clustering seperti Regular K-Means, Bisecting K-Means, dan unweighted pair group method with rithmetic mean (UPGMA) Clustering untuk menganalisis data artikel literatur dari tahun 2013 hingga 2023. Setiap algoritma dievaluasi menggunakan silhouette score dan jumlah cluster yang berbeda. Regular K-Means menghasilkan 10 cluster dengan silhouette score 0,138. Bisecting K-Means menghasilkan silhouette score 0,067 dengan jumlah cluster sebanyak 9. UPGMA Clustering menghasilkan silhouette score 0,138 dengan 10 cluster. Analisis bibliometriks menunjukan burned area dan peatland menjadi kriteria yang muncul pada hasil bibliometriks dengan masing-masing berada di kuadran yang beririsan antara 1 dan 4, dan kuadran 1 yang memiliki arti bahwa kriteria terkait merupakan tema yang penting untuk penelitian dikarenakan banyaknya jumlah penelitian terkait dan terdapat hubungan yang besar dengan penelitian lainnya dan kuadran 4 memiliki arti bahwa kriteria terkait merupakan kriteria yang tidak banyak diteliti akan tetapi banyak hubungannya dengan penelitian lainnya. Analisis hasil clustering menunjukan kriteria dan indikator berupa burned area, peatland, dan vegetation sebagai kriteria dan indikator terbanyak untuk hasil dari metode Bibliometriks dan clustering
       
      Forest and land fires in Indonesia have been an environmental issue for the past two decades, with their impacts involving various aspects. Fire impact assessments are mainly conducted for research, forest rehabilitation planning, conservation and law enforcement. However, fire impact assessment standards used as a reference for forest and land fire control are still very diverse. This research aims to identify criteria for measuring the severity of forest fires by applying Bibliometrics and text mining algorithms. In addition, the bibliometric analysis will be compared with the results of clustering analysis. This research compares several clustering algorithms such as Regular K-Means, Bisecting K-Means, and unweighted pair group method with arithmetic mean (UPGMA) Clustering to analyze literature article data from 2013 to 2023. Each algorithm was evaluated using different silhouette scores and number of clusters. Regular K-Means resulted in 10 clusters with a silhouette score of 0.138. Bisecting K-Means produced a silhouette score of 0.067 with a cluster count of 9. UPGMA Clustering produced a silhouette score of 0.138 with 10 clusters. Bibliometric analysis shows that burned area and peatland are the criteria that appear in the bibliometric results with each being in quadrants that intersect between 1 and 4, and quadrant 1 which means that related criteria are important themes for research due to the large number of related studies and there is a large relationship with other studies and quadrant 4 means that related criteria are criteria that are not widely researched but have a lot to do with other studies. Analysis of the clustering results shows criteria and indicators such as burned area, peatland, and vegetation as the most criteria and indicators for the results of the Bibliometrics and clustering methods.
       
      URI
      http://repository.ipb.ac.id/handle/123456789/157432
      Collections
      • UT - Computer Science [2482]

      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