Analisis Sentimen Sekolah Online pada Twitter dengan Algoritma Support Vector Machine

Dimas Dwi Nugroho, Arief Setyanto, Hanif Al Fatta

Abstract


                                             INTISARI
Seiring meningkatnya masyarakat yang terdampak wabah Covid-19, pemerintah akhirnya melakukan berbagai kebijakan untuk mengurangi resiko dari wabah Covid-19, salah satunya adalah Kebijakan Sekolah Online (Belajar dari rumah). Namun menteri Pendidikan dan Kebudayaan Nadiem Makarim juga mewacanakan bahwa PJJ (Pelajaran Jarak Jauh) tetap dilakukan setelah pandemi Covid-19 sudah selesai. Dari kebijakan tersebut menimbulkan berbagai opini positif dan negatif dari masyarakat, opini tersebut dapat dilihat melalui media sosial twitter. Sentimen dan opini adalah fitur penting dari keberadaan manusia. Analisis Sentimen bermaksud untuk memahami pendapat-pendapat ini dan mendistribusikannya ke dalam kategori seperti positif, netral dan negatif. Analisis sentiment saat ini terus berkembang dengan berbagai methode dan algoritma yang ada. Berdasarkan beberapa penelitian yang ada diketahui bahwa dengan menggunakan metode Algoritma Support Vector Machine dapat memberikan hasil akurasi yang lebih baik dari pada Algoritma yang lain.. Hasil penelitian dari 1200 Data tweet diperoleh Jumlah tweet netral sebanyak 445, tweet positif sebanyak 396 dan tweet negatif sebanyak 359 tweet. Dari data tersebut kemudian diproses menggunakan algoritma Support Vector Machine dan mendapatkan hasil nilai accuracy sebesar 82%, nilai Precision 83%, nilai Recall 82% dan nilai F1-Score 82 %., maka dapat disimpulkan metode Algoritma Support Vector Machine (SVM) dinilai lebih relevan untuk diterapkan pada penelitian sentiment analisis.
Kata kunci— Sentimen Analisis, SVM, Covid-19, Sekolah Online, Scrawling Twitter.

                                        ABSTRACT

Along with the increasing number of people affected by the Covid-19 outbreak, the government has finally implemented various policies to reduce the risk of the Covid-19 outbreak, one of which is the Online School Policy (Learning from home). However, the Minister of Education and Culture Nadiem Makarim also discoursed that PJJ (Distance Learning) would still be carried out after the Covid-19 pandemic was over. From this policy, it raises various positive and negative opinions from the public, these opinions can be seen through Twitter social media. Sentiments and opinions are essential features of human existence. Sentiment Analysis intends to understand these opinions and distribute them into categories such as positive, neutral and negative. Sentiment analysis is currently growing with various existing methods and algorithms. Based on several existing studies, it is known that using the Support Vector Machine Algorithm method can provide better accuracy results than other algorithms. The results of the 1200 tweet data obtained were 445 neutral tweets, 396 positive tweets and 359 negative tweets. tweets. From this data, it is processed using the Support Vector Machine algorithm and gets an accuracy value of 82%, Precision value 83%, Recall value 82% and F1-Score value 82%., it can be concluded that the Support Vector Machine (SVM) Algorithm method is considered more relevant to be applied to sentiment analysis research..
Kata kunci— Analysis Sentiment, SVM, Covid-19, Online School, Scrawling Twitter.


Keywords


Analysis Sentiment, SVM, Covid-19, Online School, Scrawling Twitter

Full Text:

 Subscribers Only


DOI: https://doi.org/10.35842/jtir.v17i3.466

Article Metrics

Abstract view : 131 times
PDF (Bahasa Indonesia) - 0 times

DOI (PDF (Bahasa Indonesia)): https://doi.org/10.35842/jtir.v17i3.466.g402

Copyright (c) 2022 Dimas Dwi Nugroho, Arief Setyanto, Hanif Al Fatta

Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 International License.

     

 
 JTI Respati (J-urnal T-eknologi I-nformasi Respati)

Fakultas Sains dan Teknologi
Universitas Respati Yogyakarta
Jl. Laksda Adisucipto KM. 6.3 Depok, Sleman, Yogyakarta, Indonesia, 55281.

Phone: 0274-488781 Email: jti@respati.ac.id Website: http://jti.respati.ac.id/index.php/

 

Creative Commons License

Jurnal Teknologi Informasi Respati is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.