Analisis Trend dan Pemetaan Penelitian Mahasiswa Teknik Informatika Menggunakan Graph Convolutional Network

  • Tifani Intan Solihati UNBAJA
  • Raden Kania UNBAJA
  • Rudianto Rudianto UBAJA
Keywords: Analysis, GCN Mapping Trend

Abstract

So far, the thesis has been compiled (during the guidance process), defended (tested in the thesis session) and revised and validated by the Advisor, Examiner, Head of Study Program, and the Dean, then collected in the library and afterwards can be used again by other students who need information the. The purpose of carrying out this research is to find student research trends and discover lecturer expertise based on the results of the work. After finding trends and expertise, the Faculty will be able to make the right decisions in determining the topic/field/study to be determined and selecting supervisors and examiners according to the scientific field and experience of the lecturer. As for the stages of the research that we will carry out, the first pre-processing stage is we conduct data providers to collect student thesis data collected in Informatics Engineering. Both learning algorithms The next stage is structured data in training data ready to be used in learning algorithms with GCN to produce candidate models and deploy selected models. Applications are the stages of applying the golden model to the testing data we have at the beginning and measuring the accuracy of the golden model. that the research trend of Informatics Engineering students is more in the field of science/the topic domain of mathematics and statistics and computer architecture. The mapping of the topic domain is 182 and 101

So far, the thesis has been compiled (during the guidance process), defended (tested in the thesis session) and revised and validated by the Advisor, Examiner, Head of Study Program, and the Dean, then collected in the library and afterwards can be used again by other students who need information the. The purpose of carrying out this research is to find student research trends and discover lecturer expertise based on the results of the work. After finding trends and expertise, the Faculty will be able to make the right decisions in determining the topic/field/study to be determined and selecting supervisors and examiners according to the scientific field and experience of the lecturer. As for the stages of the research that we will carry out, the first pre-processing stage is we conduct data providers to collect student thesis data collected in Informatics Engineering. Both learning algorithms The next stage is structured data in training data ready to be used in learning algorithms with GCN to produce candidate models and deploy selected models. Applications are the stages of applying the golden model to the testing data we have at the beginning and measuring the accuracy of the golden model. that the research trend of Informatics Engineering students is more in the field of science/the topic domain of mathematics and statistics and computer architecture. The mapping of the topic domain is 182 and 101 titles respectively. The accuracy of the GCN model determines the target class of 68.25%.

References

[1] A. Risparyanto, “Turnitin Sebagai Alat Deteksi Plagiarisme,” UNILIB J. Perpust., vol. 11, no. 2, Aug. 2020, doi: 10.20885/unilib.vol11.iss2.art5.
[2] A. R. Syahputra, “Implementasi Algoritma Winnowing Untuk Deteksi Kemiripan Judul Skripsi Studi Kasus: STMIK Budi Darma,” Pelita Inform. Budi Darma, vol. 12, no. 1, pp. 1–9, 2017.
[3] “Aplikasi Repository Pada Perpustakaan Universitas Banten Jaya,” J. Sist. Inf. dan Inform., vol. 3, no. 2, pp. 110–126, 2020, doi: 10.47080/simika.v3i2.1012.
[4] R. Vebrianto, “Trend Tema Penelitian Tugas Akhir Mahasiswa Pendidikan Kimia FTK UIN SUSKA Riau (2006-2017): Sebuah Kajian Kasus,” J. Nat. Sci. Integr., vol. 1, no. 1, pp. 1–10, 2018, doi: 10.24014/jnsi.v1i1.5182.
[5] Aptikom, Pengembangan Kurikulum KKNI Berdasarkan OBE Bidang Ilmu Informatika dan Komputer, vol. 1, no. 1. 2020.
[6] V. R. Prasetyo, N. Benarkah, and V. J. Chrisintha, “Implementasi Natural Language Processing Dalam Pembuatan Chatbot Pada Program Information Technology Universitas Surabaya,” Teknika, vol. 10, no. 2, pp. 114–121, 2021, doi: 10.34148/teknika.v10i2.370.
[7] A. Z. Arham, Klasifikasi Ulasan Buku Menggunakan Algoritma Convolutional Neural Network – Long Short Term Memory. 2018.
[8] N. de Cao, W. Aziz, and I. Titov, “Question answering by reasoning across documents with graph convolutional networks,” NAACL HLT 2019 - 2019 Conf. North Am. Chapter Assoc. Comput. Linguist. Hum. Lang. Technol. - Proc. Conf., vol. 1, pp. 2306–2317, 2019, doi: 10.18653/v1/n19-1240.
[9] L. Yao, C. Mao, and Y. Luo, “Graph Convolutional Networks for Text Detection,” Thirty-Third AAAI Conf. Artif. Intell., p. 19, 2019, [Online]. Available: www.aaai.org
[10] T. N. Kipf and M. Welling, “Semi-supervised classification with graph convolutional networks,” 5th Int. Conf. Learn. Represent. ICLR 2017 - Conf. Track Proc., pp. 1–14, 2017.
[11] X. Han et al., “The Status and Trend of Chinese News Forecast Based on Graph Convolutional Network Pooling Algorithm,” Appl. Sci., vol. 12, no. 2, pp. 1–10, 2022, doi: 10.3390/app12020900.
Published
2023-03-15