The development of software becomes important now and almost every point of view of our lives, many trends in various countries of the world in 2018 and will be interesting to follow in the following year for educational software-related developers. This study aims to analyze the relevance of the subject matter to the trend of device development research topics in order to produce sequential research between software development practicum subjects and trending topics in the world. The methodology used is a qualitative descriptive method used in analyzing the compatibility between courses, with trends in computer learning topics at the world level. Data collection is carried out through documents related to the outline categorized into 2 (two) groups. The first group deals with information relating to research trends related to publications in the journal Web of Science, SINTA, and Final Projects (TA) for Students. AMIK Indonesia. Relevance between AMIK Indonesia subject matter material and trends in relevant and supporting research topics for practicum material As a qualification of relevance for the category of high relevance with a value of 75% and above only 4 subjects, 7 moderate categories with a value of 55% to 74%, and 21 subjects with a low level of relevance, the findings that can produce material for the development of course material by supporting lecturers in each subject are specific to trending topics that are irrelevant or not supported by practicum courses that will have a positive influence on improvement quality.Keywords:Analysis, Trend Topics, Software Engineering Development, Strategies, Higher Education Curriculum.
Penelitian ini mencoba melakukan penambangan dengan menggunakan teknologi web untuk mengumpulkan data informasi yang berasal dari Web of Science dan SINTA yang dikumpulkan. Metodologi Cross Industry Standard Process for Data Mining (CRISP–DM) digunakan sebagai standard proses data mining sekaligus sebagai metode penelitian. Peneliti mengumpulkan data melalui daftar jurnal Web of Science dan SINTA. Untuk melacak trend topik penelitian, peneliti memilih rentang waktu dari tahun 2018 sampai dengan 2019 dan mengekspor data dari Web of Science Core Collection pada April 2019. Ada 38.162 publikasi yang berhasil diambil di Web-Science-defined kategori Ilmu Komputer dan Sistem Informasi dan 230 diambil dari website SINTA. Tetapi, penulis hanya mengambil 20 Jurnal dengan H-Index Tertinggi di Web of Science Core Collection. Sedangkan pada SINTA, penulis juga mengambil 20 Jurnal dengan rangking SINTA 1 dan 2. penelitian ini menyimpulkan topik penelitian dalam jurnal Web of Science dan dikaitkan dengan dengan tren topik penelitian dan yang muncul terbanyak adalah learning, network, analysis, system, control, data, image, optimization, systems, dan neural. Adapun untuk klasifikasi menggunakan model Naive Bayes, Generalized Linear Model, Logistic Regression, Fast Large Margin, Deep Learning, Decision Tree, Random Forest, Gradient Boosted Trees, dan Support Vector Machine. Berdasarkan hasil akurasi, model Generalized Linear Model dan Decision Tree memiliki akurasi sebesar 94.3%, sedangkan Gradient Boosted Trees memiliki persentase akurasi sebesar 93.8%. Naive Bayes menunjukkan tingkat akurasi sebesar 91.4%, diikuti dengan model Fast Large Margin, Deep Learning, Random Forest, dan Support Vector Machine memiliki akurasi sebesar 91.4%. Nilai dengan akurasi terendah menggunakan model Logistic Regression sebesar 65.2%. Hal ini menunjukan bahwa tingkat akurasi tertinggi yaitu dengan menggunakan model Generalized Linear Model dan Decision Tree sehingga hasilnya dapat memprediksi cukup akurat.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.