Please use this identifier to cite or link to this item: https://repository.uksw.edu//handle/123456789/25457
Title: Analisis Sentimen Transportasi Online Menggunakan Support Vector Machine Berbasis Particle Swarm Optimization
Authors: Que, Valentino Kevin Sitanayah
Keywords: analisis sentimen;Twitter;Support Vector Machine;Particle Swarm Optimization;transportasi online
Issue Date: 8-May-2020
Abstract: Terdapat fenomena transportasi online dengan masalah seperti kriminalitas dan penipuan di Indonesia yang memicu pro dan kontra pada pengguna Twitter. Makalah ini bertujuan mengetahui sentimen masyarakat terhadap transpor-tasi online dan membandingkan akurasi SVM dan SVM-PSO dengan nilai parameter default. Solusi yang diusulkan adalah membagi dataset ke dalam data training dan testing, karena beberapa penelitian mengenai optimasi hanya menggunakan satu dataset yang sudah diklasifikasikan. Data penelitian adalah data tweet dengan metode scraping menggunakan Octoparse. Total 1.852 data tweet dari 1/1/2019 hingga 15/10/2019 yang dibagi menjadi data testing 1.130 tweet dan training 722 tweet serta RapidMiner digunakan untuk proses analisis. Analisis sentimen positif menggunakan SVM adalah sebesar 62% dan sentimen negatif sebesar 38%, sedangkan pada SVM-PSO, opini positif sebesar 53% dan negatif 47%. Hasil penelitian menggunakan 10 k-fold CV menghasilkan akurasi pada SVM sebesar 95,46% dan AUC 0,979 (excellent classification), sedangkan pada SVM-PSO sebesar 96,04% dan AUC 0,993 (excellent classification). Hasil menunjukkan bahwa penggunaan data training dan testing dapat dilakukan dan terbukti bahwa SVM-PSO lebih baik daripada SVM biasa, meskipun menggunakan nilai parameter default.
Phenomenon of online transportation with some problems like crime and fraud in Indonesia triggers pros and cons to Twitter users. This study aims to find out sentiments of the society on online transportation and compare the accuracy of SVM and SVM-PSO with default parameters value. The proposed solution divided the dataset into training and testing data, because some researches only used one dataset that had already been classified. The research data is tweet data, which is obtained through scraping method using Octoparse. A total of 1.852 tweets from 1/1/2019 to 15/10/2019 were divided into 1.130 tweet testing data and 722 tweet training data. Then, RapidMiner was used for analysis process. Analysis positive sentiment using SVM is 62% and negative sentiment is 38%, while in SVM-PSO, positive opinion is 53% and negative opinion is 47%. The results of research using 10 k-fold CV produce accuracy on SVM is 95,46% and AUC is 0,979 (excellent classification), while in SVM-PSO accuracy is 96,04% and AUC is 0,993 (excellent classification). The results show that use of training and testing data on this study can be done and prove that SVM-PSO is better than ordinary SVM, although the parameters value is default.
URI: https://repository.uksw.edu/handle/123456789/25457
Appears in Collections:T2 - Master of Information Systems

Files in This Item:
File Description SizeFormat 
T2_972017016_Abstract.pdfAbstract58.85 kBAdobe PDFView/Open
T2_972017016_Full text.pdf
  Until 2999-01-01
Full text2.02 MBAdobe PDFView/Open Request a copy


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.