Klasifikasi Sentimen Pada Twitter Dalam Membantu Pemilihan Kandidat Karyawan Dengan Menggunakan Convolutional Neural Network Dan Fasttext Embeddings

Authors

  • Farhan Alfariqi Telkomuniversity
  • Warih Maharani Telkomuniversity
  • Jati Hiliamsyah Husen Telkomuniversity

DOI:

https://doi.org/10.34818/eoe.v7i2.13085

Abstract

Abstrak Karyawan merupakan elemen utama yang dapat meningkatkan nilai dari suatu perusahaan. Menemukan karyawan yang berkualitas umumnya memerlukan proses yang cukup rumit. Proses penerimaan karyawanmenjaditahapanawalyangberperanpentingdalammewujudkanhaltersebut. Prosespenerimaanyang buruk akan berdampak pada tingginya angka resign karyawan yang biasanya disebut dengan nilai turnover. Permasalahantersebutdapatdiatasisalahsatunyadengancaramengamatikandidatkaryawanmelalui aktiï¬tas sosial media. Berdasarkan hasil analisis tersebut, perusahaan dapat secara langsung mengetahui sikapdansifatdaritiapcalonkaryawan,sehinggadapatmenjadipertimbangandalammemilihkaryawan. Data yang digunakan dalam penelitian diambil dari media sosial Twitter sebanyak 3583 komentar yang dibagi menjadi tiga sentimen yaitu positif, netral dan negatif. Komentar yang diperoleh direduksi dengan caramenghapuskata,angkamaupunsimbolyangtidakmemilikiinformasidanmaknayangpenting. Kumpulan kata hasil reduksi diubah menjadi bentuk vektor dengan menggunakan fasttext. Hasil dari fasttext menjadiinputpelatihanmodelConvolutionalNeuralNetwork. Berdasarkanhasilpengujianyangdilakukanpada20calonkaryawan, kombinasifasttextdanConvolutional Neural Network dengan beberapa aturan hyperparameter mampu memberikan nilai akurasi terbaik sebesar 84.01%. Nilai akurasi yang dihasilkan tersebut dapat menjadi patokan bahwa model yang dibangunmampumembantupihakperusahaandalammemilihcalonkaryawan. Katakunci: sentimen,karyawan,seleksi,fasttext,CNN Abstract Employees are the main element that can increase the value of a company. Finding qualiï¬ed employees generally requires a somewhat complicated process. The recruitment process is the initial stage that plays an essential role in realizing this. The imperfect admission process will impact the high employee resign rate, which usually refers to the turnover value. One of the problems can overcome by observing employee candidates through social media activities. Based on the results of the analysis, the company can directly knoweachemployee’sattitudes,sothatitcanconsiderinselectingemployees. The data used in the study were taken from Twitter social media as many as 3583 comments divide into threesentiments,namelypositive,neutral,andnegative. Observationsobtainedreducebyremovingwords, numbers, or symbols that do not have valuable information and meaning. The deduction words are convertedintovectorshapesusingfasttext. TheresultsoffasttextbecometraininginputfortheConvolutional NeuralNetworkmodel. Basedontheresultsoftestsconductedon20prospectiveemployees,thecombinationoffasttextandConvolution Neural Network with several hyperparameter rules can provide the best accuracy value of 84.01%. The resulting accuracy can be a benchmark that the model built is ready to help the company select prospectiveemployees. Keywords: sentiment,employees,selection,fasttext,CNN

Downloads

Download data is not yet available.

References

[1] Hermin Endratno. Talent management dalam meningkatkan kinerja organisasi. Sustainable Competitive Advantage (SCA), 1(1), 2013.

[2] Emillia Nurdin, Andi Basru Wawo, and Lilis Julia. Pengaruh pengembangan kapasitas sumber daya manusia aparatur pemerintah daerah terhadap kinerja pegawai (studi pada badan pengelola keuangan dan aset daerah kota kendari). Jurnal Akuntansi dan Keuangan, 3(1):1–13, 2018.

[3] Xiang Zhang, Junbo Zhao, and Yann LeCun. Character-level convolutional networks for text classification. In Advances in neural information processing systems, pages 649–657, 2015.

[4] Igor Santos, Nadia Nedjah, and Luiza de Macedo Mourelle. Sentiment analysis using convolutional neural network with fasttext embeddings. In 2017 IEEE Latin American Conference on Computational Intelligence (LA-CCI), pages 1–5. IEEE, 2017.

[5] Armand Joulin, Edouard Grave, Piotr Bojanowski, and Tomas Mikolov. Bag of tricks for efficient text classification. In Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 2, Short Papers, pages 427–431, Valencia, Spain, April 2017. Association for Computational Linguistics.

[6] Tomas Mikolov, Kai Chen, Greg Corrado, and Jeffrey Dean. Efficient estimation of word representations in vector space. In Yoshua Bengio and Yann LeCun, editors, 1st International Conference on Learning Representations, ICLR 2013, Scottsdale, Arizona, USA, May 2-4, 2013, Workshop Track Proceedings, 2013.

[7] Piotr Bojanowski, Edouard Grave, Armand Joulin, and Tomas Mikolov. Enriching word vectors with subword information. Transactions of the Association for Computational Linguistics, 5:135–146, 2017.

[8] Yoon Kim. Convolutional neural networks for sentence classification. In Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 1746–1751, Doha, Qatar, October 2014. Association for Computational Linguistics.

[9] Xi Ouyang, Pan Zhou, Cheng Hua Li, and Lijun Liu. Sentiment analysis using convolutional neural network. In 2015 IEEE International Conference on Computer and Information Technology; Ubiquitous Computing and Communications; Dependable, Autonomic and Secure Computing; Pervasive Intelligence and Computing, pages 2359–2364. IEEE, 2015.

[10] Bo Pang and Lillian Lee. Seeing stars: Exploiting class relationships for sentiment categorization with respect to rating scales. In Proceedings of the 43rd annual meeting on association for computational linguistics, pages 115–124. Association for Computational Linguistics, 2005.

[11] Xinyang Deng, Qi Liu, Yong Deng, and Sankaran Mahadevan. An improved method to construct basic probability assignment based on the confusion matrix for classification problem. Information Sciences, 340:250–261, 2016.

Downloads

Published

2020-08-01

Issue

Pages

8052-8062

Section

Program Studi S1 Informatika

How to Cite

Alfariqi, F., Maharani, W., & Husen, J. H. (2020). Klasifikasi Sentimen Pada Twitter Dalam Membantu Pemilihan Kandidat Karyawan Dengan Menggunakan Convolutional Neural Network Dan Fasttext Embeddings. EProceedings of Engineering, 7(2), 8052-8062. https://doi.org/10.34818/eoe.v7i2.13085