Sistem Rekomendasi Pekerjaan Menggunakan Content Based Similarity

Abdur Rouf(1*),Yuliana Melita Pranoto(2),Endang Setyati(3)
(1) Mahasiswa Institut Teknik Dan Sains Terpadu Surabaya
(2) Institut Sains Dan Teknologi Terpadu Surabaya
(3) Institut Sains Dan Teknologi Terpadu Surabaya
(*) Corresponding Author
DOI : 10.35889/jutisi.v12i2.1229

Abstract

Based on data from the Central Statistics Agency (BPS) it is stated that the data for people who did not have a job from August 2019 to August 2021 recorded an increase from 7104.42 to 9102.05, meaning that within 2 years people who did not have a job had increased significantly. This is caused by one of the factors, namely finding information on job vacancies which is difficult, users still have to choose one job at a time in accordance with their field of knowledge. By building a job recommendation system, users will find it easier to find suitable job information, the data used is obtained from 1120 (one thousand one hundred and twenty) alumni data which includes academic grades, non-academic scores, positions and companies obtained from alumni data from the Institute of Technology and Business Widya Gama Lumajang. Using a content-based similarity algorithm with machine learning techniques using the MLP classifier feature and several trials using different parameters in each experiment. In each experiment the researcher used 10 (ten) samples. The results of this trial the machine learning feature of the MLP classifier can be concluded to be able to provide an accuracy of 81% with a precision value of 0.77, a recall of 0.81 and an f1-score of 0.76.The results of this study are used by users or fresh graduates to get job recommendations in accordance with their field of study.

Keywords: Content Based Similarity; Interaciton Based Relation; Job Recommendation System

 

Abstrak

Berdasarkan data Badan Pusat Statistik (BPS) menyebutkan bahwa data orang yang tidak memiliki pekerjaan dari agustus 2019 sampai dengan agustus 2021 tercatat naik dari angka 7.104,42 menjadi 9.102,05 artinya dalam kurun 2 tahun orang yang tidak memiliki pekerjaan mengalami kenaikan secara signifikan. Hal ini disebabkan oleh salah satu faktor yaitu mencari informasi lowongan pekerjaan yang sulit pengguna masih harus memilih satu per satu pekerjaan yang sesuai dengan bidang ilmunya. Dengan membangun sistem rekomendasi pekerjaan pengguna akan lebih mudah menemukan informasi pekerjaan yang sesuai, data yang digunakan diperoleh dari data alumni sebanyak 1.120 (seribu seratus dua puluh) yang mencakupi nilai akademik, nilai non akademik, jabatan dan perusahaan yang diperoleh dari data alumni Institut Teknologi Dan Bisnis Widya Gama Lumajang. Menggunakan algoritma content-based similarity dengan teknik machine learning fitur MLP classifier dan beberapa kali uji coba menggunakan parameter yang berbeda-beda pada setiap percobaannya. Pada setiap percobaan peneliti memakai 10 (sepuluh) sample. Hasil dari uji coba ini machine learning fitur MLP classifier dapat disimpulkan mampu memberikan akurasi sebesar 81% dengan nilai precision 0.77 recall 0.81 dan f1-score 0.76. Hasil penelitian ini digunakan oleh pengguna atau fresh graduate untuk mendapatkan rekomendasi pekerjaan yang sesuai dengan bidang ilmu.

 

Keywords


Content Based Similarity; Interaciton Based Relation; Sistem Rekomendasi Pekerjaan

References


Badan Pusat Statistik, “Data Badan Pusat Statistik (BPS) dari bulan agustus 2019 sampai dengan bulan agustus tahun 2021 tercatat naik dari angka 7 104,42 menjadi 9102,05 artinya dalam kurun waktu 2 tahun orang yang tidak mempunyai pekerjaan bertambah 1997,63.” https://www.bps.go.id/.

X. Guo, H. Jerbi, dan M. P. O’Mahony, “An Analysis Framework for Content-based Job Recommendation”.

Databoks Katadata, “BPS: Sarjana yang Menganggur Hampir 1 Juta Orang pada Februari 2021.” [Daring]. Tersedia pada: https://databoks.katadata.co.id/

F. Nurfalah, Asriyanik, dan A. Pambudi, “Sistem Rekomendasi Event Online Menggunakan Metode Content Based Filtering,” Elkom J. Elektron. Dan Komput., vol. 15, no. 2, hlm. 271–279, Des 2022, doi: 10.51903/elkom.v15i2.736.

M. Yusuf dan A. Cherid, “Implementasi Algoritma Cosine Similarity Dan Metode TF-IDF Berbasis PHP Untuk Menghasilkan Rekomendasi Seminar,” vol. 9, no. 1, 2020, [Daring]. Tersedia pada: https://publikasi.mercubuana.ac.id/index.php/fasilkom/article/view/8830

W. Hong, S. Zheng, H. Wang, dan J. Shi, “A Job Recommender System Based on User Clustering,” J. Comput., vol. 8, no. 8, hlm. 1960–1967, Agu 2013, doi: 10.4304/jcp.8.8.1960-1967.

N. D. Almalis, G. A. Tsihrintzis, N. Karagiannis, dan A. D. Strati, “FoDRA — A new content-based job recommendation algorithm for job seeking and recruiting,” dalam 2015 6th International Conference on Information, Intelligence, Systems and Applications (IISA), Corfu: IEEE, Jul 2015, hlm. 1–7. doi: 10.1109/IISA.2015.7388018.

S. Bansal, A. Srivastava, dan A. Arora, “Topic Modeling Driven Content Based Jobs Recommendation Engine for Recruitment Industry,” Procedia Comput. Sci., vol. 122, hlm. 865–872, 2017, doi: 10.1016/j.procs.2017.11.448.

D. Behl, S. Handa, dan A. Arora, “A bug Mining tool to identify and analyze security bugs using Naive Bayes and TF-IDF,” dalam 2014 International Conference on Reliability Optimization and Information Technology (ICROIT), Faridabad, Haryana, India: IEEE, Feb 2014, hlm. 294–299. doi: 10.1109/ICROIT.2014.6798341.

M. Purkar, O. Joshi, A. Salape, A. Patil, V. Kulkarni, dan P. Futane, “Recommendation System for Workers & Customers for Informal Jobs,” dalam SSRN Electronic Journal, Vishawakarma Institut of Information Technology: Vishawakarma Institut of Information Technology, 2021, hlm. 1–6. doi: 10.2139/ssrn.3833762.

J. Wintrode, G. Sell, A. Jansen, M. Fox, D. Garcia-Romero, dan A. McCree, “Content-based recommender systems for spoken documents,” dalam 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), South Brisbane, Queensland, Australia: IEEE, Apr 2015, hlm. 5201–5205. doi: 10.1109/ICASSP.2015.7178963.

Nurtiyasari, Devi dan Syarif, Mulkan, “Belajar Algoritma Multi Layer Percepton Continue reading at Belajar Algoritma Multi Layer Percepton | Softscients,” Belajar Algoritma Multi Layer Percepton Continue reading at Belajar Algoritma Multi Layer Percepton | Softscients, 2020. https://softscients.com/2020/11/05/belajar-algoritma-multi-layer-percepton/

R. H. Mondi dan A. Wijayanto, “Recommendation System With Content-Based Filtering Method For Culinary Tourism In Mangan Application,” ITSMART : Jurnal Teknologi dan Informasi, vol. 8, no. 2, hlm. 65–72, 2019, doi: https://doi.org/10.20961/itsmart.v8i2.35008.

M. Irfan, Cahyani,Andriani D, dan Hastarita, Fika, “Sistem Rekomendasi: Buku Online Dengan Metode Collaborative Filtering,” Jurnal Teknologi Technoscientia, vol. 7, no. 1, hlm. 76–84, 2014, doi: https://doi.org/10.34151/ technoscientia.v7i1.612.

S. Dong, Z. Lei, P. Zhou, K. Bian, dan G. Liu, “Job and Candidate Recommendation with Big Data Support: A Contextual Online Learning Approach,” dalam GLOBECOM 2017 - 2017 IEEE Global Communications Conference, Singapore: IEEE, Des 2017, hlm. 1–7. doi: 10.1109/GLOCOM.2017.8255006.

I. W. Jepriana dan S. Hanief, “Analisis Dan Implementasi Metode Item-Based Collaborative Filtering Untuk Sistem Rekomendasi Konsentrasi Di Stmik Stikom Bali,” Jurnal Nasional Pendidikan Teknik Informatika: JANAPATI, vol. 9, no. 2, hlm. 171–180, 2020, doi: https://doi.org/10.23887/janapati.v9i2.23218.


The PDF file you selected should load here if your Web browser has a PDF reader plug-in installed (for example, a recent version of Adobe Acrobat Reader).

If you would like more information about how to print, save, and work with PDFs, Highwire Press provides a helpful Frequently Asked Questions about PDFs.

Alternatively, you can download the PDF file directly to your computer, from where it can be opened using a PDF reader. To download the PDF, click the Download link above.

Fullscreen Fullscreen Off

Full Text: File PDF (Indonesian)

How To Cite This :

Refbacks

  • There are currently no refbacks.