Jurnal SINTA 2
Prediksi Bidang Penelitian dan Rekomendasi Dosen Pembimbing Skripsi Berdasarkan Konten Latar Belakang pada Naskah Proposal Menggunakan Metode Multi-Class Support Vector Machine dan Weighted Product
Jurnal Teknologi Informasi dan Ilmu Komputer (JTIIK) · Vol. 8 No. 2 (2021) · pp. 403–410
- ISSN
- 2528-6579, 2355-7699
- Published
- 2021-03-25
- Publisher
- Fakultas Ilmu Komputer, Universitas Brawijaya
- Language
- id
Abstract
Pada Fakultas Ilmu Komputer Universitas Brawijaya (FILKOM UB), pengerjaan skripsi dimulai dengan melakukan pembuatan praproposal yang berisi latar belakang dan bidang skripsi. Dalam pengerjaan skripsi, mahasiswa butuh pendampingan oleh dosen pembimbing. Dosen pembimbing berfungsi sebagai motivator, pendamping serta pemberi arahan bagi mahasiswa yang sedang mengerjakan skripsi. Dosen pembimbing menjadi krusial dalam pengerjaan skripsi seorang mahasiswa. Oleh karena hal tersebut, pemilihan dosen pembimbing yang memiliki bidang keahlian yang sesuai dengan topik skripsi sangat penting. Pada FILKOM UB, dosen dengan bidang keahlian yang serupa dikumpulkan dalam sebuah kelompok jabatan fungsional dosen (KJFD). Mahasiswa FILKOM UB dapat berdiskusi dengan ketua program studi atau koordinator KJFD untuk mendapatkan rekomendasi dosen yang memiliki bidang keahlian sesuai topik skripsi. Topik skripsi dapat ditentukan dari latar belakang sebuah proposal skripsi. Penelitian ini bertujuan untuk mengetahui tingkat akurasi prediksi KJFD menggunakan algoritme Multi-class Support Vector Machine dan tingkat akurasi rekomendasi dosen pembimbing menggunakan algoritme Weighted Product. Prediksi KJFD dilakukan berdasarkan latar belakang pada naskah skripsi. Rekomendasi dosen diberikan berdasarkan kesesuaian bidang KJFD dosen dengan topik dan beberapa data dosen yang didapatkan dari unit Pengelola Sistem Informasi, Infrastruktur TI dan Kehumasan Fakultas Ilmu Komputer (PSIK FILKOM) seperti jurusan dosen, sisa kuota bimbingan, tingkatan gelar, dan beban kerja. Hasil pengujian menghasilkan akurasi prediksi bidang skripsi memiliki nilai precision tertinggi sebesar 0,93 dan akurasi rekomendasi dosen pembimbing memiliki nilai precision@k tertinggi sebesar 0,1678 saat nilai k berjumlah 4. Hasil pengujian akurasi tersebut menampilkan bahwa prediksi bidang skripsi dapat dilakukan dengan sangat baik menggunakan Multi-class Support Vector Machine. Sementara rekomendasi dosen pembimbing dapat dilakukan secara optimal dengan jumlah dosen yang direkomendasikan sebanyak 4 dosen.AbstractIn Fakultas Ilmu Komputer Universitas Brawijaya (FILKOM UB), thesis work started by making preproposal which contains the background and thesis field/topic. In the working of thesis, undergraduate student needs to be accompanied by a supervisor. Supervisor serve as motivator, companion, and guider for undergraduate students who are doing their thesis research. Supervisor roles become crucial in the working of thesis. Therefore, the selection of supervisor who have areas of expertise that matching with thesis topic is very important. In FILKOM UB, supervisor with similar expertise gathered in a lecturer functional group (KJFD). Students of FILKOM UB may discuss with the head of programme or KJFD coordinator to get a supervisor reccomendation who suitable with the topic of thesis. The topic of thesis can be determined by the introduction contents in proposal manuscript. This research aims to discover the accuracy of KJFD prediction using Multi-class Support Vector Machine and the accuracy of supervisor reccomendation using Weighted Product. KJFD prediction formulated based on introduction contents in proposal manuscript. Supervisor recommendation done based on the coherency of supervisor’s expertise with the thesis’s topic and also based on some supervisor data that was obtained from unit Pengelola Sistem Informasi, Infrastruktur TI dan Kehumasan Fakultas Ilmu Komputer (PSIK FILKOM). The data that was obtained from unit PSIK FILKOM are supervisor’s majors, remaining quota for supervising, degree level, and work load. Testing result shows the accuracy of thesis’s topic having precision value of 0,93 and accuracy of the supervisor predicition having precision@k value of 0,1678 with k value of 4. The accuracy test result shows that thesis topics prediction can be done very well using Multi-class Support Vector Machine. While supervisor reccomendation can be done optimally when the number of recommended supervisor is 4.
Collaboration network of the authors
40 authors · 78 co-authorship links · 18 across different organisations · showing the 40 most connected
Hover or tap a name to highlight its co-authors. Double-click to open the author's page.
- University of Brawijaya
- Indonesian Institute of Sciences
- National Research and Innovation Agency
- Universitas Gadjah Mada
- Affiliation unknown
- Different organisations
- Same organisation
- Affiliation unknown
- Thicker line = more joint articles · bigger circle = more articles
Show as table
| Co-author | Organisation | Joint articles |
|---|---|---|
| Satrio Hadi Wijoyo | University of Brawijaya | 4 |
| Nanang Yudi Setiawan | University of Brawijaya | 2 |
| Vicky Zilvan | Indonesian Institute of Sciences | 2 |
| Asri Rizki Yuliani | Indonesian Institute of Sciences | 2 |
| Ade Ramdan | Indonesian Institute of Sciences | 2 |
| Sutrisno . | Affiliation unknown | 2 |
| Tibyani Tibyani | University of Brawijaya | 2 |
| Buce Trias Hanggara | University of Brawijaya | 2 |
| Hanifah Muslimah Az-Zahra | University of Brawijaya | 2 |
| Hilman Ferdinandus Pardede | National Research and Innovation Agency | 2 |
| Nur Laita Rizki Amalia | University of Brawijaya | 1 |
| Imam Cholissodin | University of Brawijaya | 1 |
| Candra Dewi | University of Brawijaya | 1 |
| Dany Primanita Kartikasari | University of Brawijaya | 1 |
| Budi Darma Setiawan | University of Brawijaya | 1 |
| Farhanna Mar’i | University of Brawijaya | 1 |
| Rizal Arif Zulfikar | University of Brawijaya | 1 |
| I Putu Pradnyana Iswara | University of Brawijaya | 1 |
| Irvi Oktanisa | University of Brawijaya | 1 |
| Aditya Hari Bawono | University of Brawijaya | 1 |
| Suprapto Suprapto | Universitas Gadjah Mada | 1 |
| Muhammad Ghiffari | University of Brawijaya | 1 |
| Muhamad Rifky | University of Brawijaya | 1 |
| Bondan Sapta Prakoso | University of Brawijaya | 1 |
| Nabila Divanadia Luckyana | University of Brawijaya | 1 |
| Fara Regina Isadora | University of Brawijaya | 1 |
| Aditya Rachmadi | University of Brawijaya | 1 |
| Audi Kresna Fathurino | University of Brawijaya | 1 |
| Komang Candra Brata | University of Brawijaya | 1 |
| Santi Yunika Sufiana | University of Brawijaya | 1 |
| Roshidah Nur Halimah | University of Brawijaya | 1 |
| Alfi Nur Rusydi | University of Brawijaya | 1 |
| Anisah Ikhsawiyanthi | University of Brawijaya | 1 |
| Safira Nur Rahmah | University of Brawijaya | 1 |
| Pradya Mutiarahma | University of Brawijaya | 1 |
| Widhy Hayuhardhika Nugraha Putra | University of Brawijaya | 1 |
| Reyhan Ivandi | University of Brawijaya | 1 |
Affiliations come from OpenAlex; journal OAI-PMH metadata carries none. Authors without an OpenAlex ID are matched by name, which can merge or split people.