Article Per Year (5 Year)
p-Index From 2019 - 2024
0.444
P-Index
This Author published in this journals
All Journal Indonesian Journal of Electrical Engineering and Computer Science Jurnal Kajian Ilmiah
Amsal Pardamean
STMIK Nusa Mandiri
Humanities Computer Science & IT Economics, Econometrics & Finance Education Social Sciences

Published : 2 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 2 Documents
Search

 1 
Sentimen Analisis Publik Terhadap Joko Widodo terhadap wabah Covid-19 menggunakan Metode Machine Learning Sisferi Hikmawan; Amsal Pardamean; Siti Nur Khasanah
Jurnal Kajian Ilmiah Vol. 20 No. 2 (2020): Mei 2020
Publisher : Lembaga Penelitian, Pengabdian Kepada Masyarakat dan Publikasi (LPPMP)

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (532.285 KB) | DOI: 10.31599/jki.v20i2.117

Abstract

Abstract Analyzing public sentiment towards a government policy is no longer impossible, the process of analyzing with data mining is a method that is often used. The Data Mining method is always related to the dataset, with the keywords "Jokowi" and "Covid" twitter allowing us to make tweets in it to be used as a dataset. In data mining for sentiment analysis, techniques such as transform, tokenize, stemming, classification, etc. are very influential on its accuracy. Gata Framework is used for preprocessing, and Rapidminer is also used to analyze and compare three classification methods namely Naive Bayes, Support Vector Machine, and k-NN. And the best value is obtained, the Support Vector Machine with an accuracy of 84.58%, precision 82.14% and recall 85.82%. Keywords: Covid, Jokowi, SVM, K-NN, Naive Bayes Abstrak Menganalisa sentimen publik terhadap suatu kebijakan pemerintah merupakan cara yang tidak lagi mustahil, proses analisa dengan data mining merupakan metode yang sering digunakan. Metode Data Mining selalu berkaitan dengan dataset, dengan kata kunci “Jokowi” dan “Covid” twitter memungkinkan kita menjadikan tweet didalamnya untuk dijadikan dataset. Dalam data mining untuk sentimen analisis, dilakukan teknik seperti transform, tokenize, stemming, classification, dan lain-lain sangat berpengaruh pada akurasinya. Gata Framework digunakan untuk preprocessing, dan Rapidminer juga digunakan untuk menganalisa dan membandingkan tiga metode klasifikasi yaitu Naive Bayes, Support Vector Machine, dan k-NN. Dan dihasilkan nilai terbaik yaitu Support Vector Machine dengan accuracy 84.58%, precision 82.14% dan recall 85.82%. Kata kunci: Covid, Jokowi, SVM, K-NN, Naive Bayes
Tuned bidirectional encoder representations from transformers for fake news detection Amsal Pardamean; Hilman F. Pardede
Indonesian Journal of Electrical Engineering and Computer Science Vol 22, No 3: June 2021
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijeecs.v22.i3.pp1667-1671

Abstract

Online medias are currently the dominant source of Information due to not being limited by time and place, fast and wide distributions. However, inaccurate news, or often referred as fake news is a major problem in news dissemination for online medias. Inaccurate news is information that is not true, that is engineered to cover the real information and has no factual basis. Usually, inaccurate news is made in the form of news that has mass appeal and is presented in the guise of genuine and legitimate news nuances to deceive or change the reader's mind or opinion. Identification of inaccurate news from real news can be done with natural language processing (NLP) technologies. In this paper, we proposed bidirectional encoder representations from transformers (BERT) for inaccurate news identification. BERT is a language model based on deep learning technologies and it has found effective for many NLP tasks. In this study, we use transfer learning and fine-tuning to adapt BERT for inaccurate news identification. The experiments show that our method could achieve accuracy of 99.23%, recall 99.46%, precision 98.86%, and F-Score of 99.15%. It is largely better than traditional method for the same tasks.
Co-Authors Hilman F. Pardede Sisferi Hikmawan Siti Nur Khasanah