• Kode Repository : SKI /MUH/19
• NPM : 065112225
• Nama : Muhamad Zuhri
• Pembimbing 1 : -Arie Qur'ania M.Kom
• Pembimbing 2 : -Mulyati, M.Kom.
• Abstrak : -Analisis Sentimen Terhadap Opini Penggunaan Gawai Pada Siswa Menggunakan Metode Support Vector Machine (SVM) Muhamad Zuhri1), Arie Qur’ania2), Mulyati3) 1, 2 & 3)Program Studi Ilmu Komputer, FMIPA, Universitas Pakuan Bogor 1)mhmdzuhry05@gmail.com, 2)qurania@unpak.ac.id 3)mulyati@unpak.ac.id Abstract Sentiment Analysis is a field of science in analyzing a sentiment or opinion on a particular object or problem and the opinion can be divided into several purposes (classes) that lead to negative, neutral or positive opinions. Gadgets (gadgets) are human aids in many fields including work, entertainment, communication and information, the use of gadgets themselves encompasses all ages including school students who use gadgets excessively that affect the mental, physical and attitudes of users. Twitter social media is one of the social media that is used by the public in making opinions about the influence of gadgets, especially parents, these opinions are useful for other users in determining the granting of access rights and direction for children, especially students in using gadgets. Opinion classification is needed in making it easier for other users to see whether opinions from the influence of gadgets fall into the negative, neutral or positive classes. The method used in the classification of opinion is Support Vector Machine (SVM). The data used in this study amounted to 1354 taken in 2019 using web scraping techniques on the Twitter site which are then pre-processed so that it can be processed into the program and classified into 3 classes of sentiments, namely negative, neutral and positive sentiments. In finding the average value of accuracy in the distribution of training data and test data using k-fold cross validation of 10 fold produces an average value of 85.3%. Then testing is done to measure the performance of the SVM method using confusion matrix in the percentage of training data and different test data and produces the highest accuracy value of 83.3%, as well as testing manually from the program sample data output with the original data and get an accuracy value of 82.3%. Keywords: Sentiment analysis, Twitter, Support Vector Machine, K-fold Cross Validation, Confusion Matrix
• Program Studi : Ilmu Komputer