Abstract

The Pandemic Covid-19 in Indonesia in 2020 had an impact on Termination of Employment (PHK), this has received various public opinions on social media. At a time when the poverty rate is high and unemployment increases every year, it becomes a factor of public disapproval of Termination of Employment (PHK). It is necessary to classify public opinion into a negative opinion or a positive opinion on this issue. The purpose of this study is to analyze the sentiment towards layoffs to determine negative or positive opinions using the Naïve Bayes algorithm by adding feature selection. The research stages consist of data collection, text preprocessing, feature selection, and application of algorithms. The testing process in this study uses the Rapid Miner application. The test results in this study using the Naive Bayes Algorithm, the accuracy value is 93.57% and for addition to the Naïve Bayes + PSO feature selection, the accuracy value is 93.71%. The best accuracy value in sentiment analysis of layoffs in the covid-19 pandemic is the addition of the PSO feature selection in the Naïve Bayes Algorithm, which is 0.14% better.

Highlights

  • Abstrak – Pandemic Covid-19 di Indonesia tahun 2020 berimbas pada Pemutusan Hubungan Kerja (PHK), hal ini mendapatkan opini masyarakat yang beragam di dalam media sosial

  • The purpose of this study is to analyze the sentiment towards layoffs to determine negative or positive opinions using the Naïve Bayes algorithm by adding feature selection

  • The test results in this study using the Nave Bayes Algorithm, the accuracy value is 93.57% and for addition to the Naïve Bayes + Particle Swarm Optimazation (PSO) feature selection the accuracy value is 93.71%

Read more

Summary

PENDAHULUAN

Coronavirus Disease-2019 (COVID-19) merupakan salah satu virus berbahaya yang menyebabkan penyakit infeksi saluran pernapasan berkepanjangan dan sampai mengakibatkan meninggal dunia. Indonesia merupakan negara ke-24 yang terkena dampak pandemi COVID-19 yaitu sebesar 97.286 jiwa positif COVID-19 dengan 55.354 jiwa sembuh dan sebanyak 4.714 meninggal dunia[1]. Dampak dari perusahaan terhadap produksi secara tidak langsung akan menurun dengan adanya social distancing yaitu dengan memberikan kebijakan terhadap karyawannya misalnya dirumahkan, bekerja bergantian, pengurangan gaji, atau Pemutusan Hubungan Kerja (PHK). Pemutusan Hubungan Kerja (PHK) menjadi pembicaraan yang sangat menarik karena telah menimbulkan opini masyarakat dalam media sosial. Analisis Sentimen dapat mengklasifikasikan opini yang terkandung dalam Twitter bisa menggunakan algoritma Naïve Bayes. Pada penelitian ini akan dilakukan analisis sentimen terhadap Pemutusan Hubungan Kerja (PHK) dengan menggunakan algoritma yaitu Naïve Bayes ditambahan feature selection PSO. Peneliti berharap dapat meningkatkan nilai accuracy, sehingga akan ditemukan hasil terbaik untuk analisis sentimen terhadap Pemutusan Hubungan Kerja (PHK) perusahaan di Indonesia.

Data Mining
Text Mining
Naïve Bayes
Feature Selection
Sentiment Analysis
Twitter
Tahapan Penelitian
Data Trainning dan Data Testing
Process Document
Proses Pengujian
HASIL DAN PEMBAHASAN
Hasil Penelitian
Findings
Pengujian Naïve Bayes
Full Text
Paper version not known

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call

Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.