Artikel
Judul : Analisis Sentimen terhadap Hasil Pilpres 2019 dengan Membandingkan Algoritma Support Vector Machine
Abstrak : The election of the president of the Republic of Indonesia is widely discussed in the real world and cyberspace, especially on Twitter social media. Today the development of social media as a tool for communicating among the public to convey opinions, all people are free to have an opinion about candidates for President and Vice President of Indonesia in 2019 so that there are appear many opinions, both opinions with positive, negative or neutral sentiments towards candidates for President and Vice President. This study was conducted to compare the effectiveness of the Support Vector Machine (SVM) algorithm with the K- Nearest Neighbor (KNN) algorithm and predict the results of the presidential election based on sentiment. In this study a comparison of the SVM algorithm and the KNN algorithm was carried out to classify sentiments against Presidential candidates in the 2019 Presidential Election with data obtained from Twitter. Preprocessing and weighting are done using TF-IDF. SVM algorithm has the highest accuracy results compared to the KNN algorithm. The average accuracy of the SVM algorithm is 69.27 with the highest accuracy of 76.5%, while the average value of the KNN algorithm is 61.3% with the highest accuracy of 68.3%. The fastest training time was obtained by the KNN algorithm while the fastest testing time was obtained by the SVM algorithm compared to the KNN and the president's prediction results based on the most positive sentiment namely candidate number 02 with 85.4% while the number of candidates for positive sentiment number 01 was 76.8%.
Penulis : Fiki Firmansyah
Keyword : Accuracy, Comparison, Presidential Election 2019, Sentiment Analysis, twitter.
Referensi : [1] R. M. H., “Analisis sentimen pada twitter menggunakan metode naïve bayes (studi kasus pemilihan gubernur dki jakarta 2017) muhammad hadiyan rasyadi,” 2017. [2] W. C. Widyaningtyas and S. Al Faraby, “Klasifikasi Sentiment Analysis pada Review Film Berbahasa Inggris dengan Menggunakan Metode Doc2Vec dan Support Vector Machine ( SVM ) Sentiment Analysis Classification of Movie Review in English Language using Doc2Vec and Support Vector Machine ( SVM ),” vol. 5, no. 1, pp. 1570–1578, 2018. [3] S. Budi, “Text Mining Untuk Analisis Sentimen Review Film Menggunakan Algoritma K-Means,” J. Teknol. Inf., vol. 16, no. 1, pp. 1–8, 2017. [4] M. Chairul Fauzi, “MASYARAKAT TERHADAP CALON GUBERNUR JAWA BARAT TAHUN 2018 MENGGUNAKAN METODE NAIVE BAYES CLASSIFIER PADA TWITTER,” 2018. [5] A. Pratama, R. C. Wihandika, and D. E. Ratnawati, “Implementasi Algoritme Support Vector Machine ( SVM ) untuk Prediksi Ketepatan Waktu Kelulusan Mahasiswa,” J. Pengemb. Teknol. Inf. dan Ilmu Komput. e-ISSN, 2548, 964X, vol. 2, no. 4, pp. 1704–1708, 2018. [6] V. Chandani, S. R. Wahono, and Purwanto, “Komparasi Algoritma Klasifikasi Machine Learning Dan Feature Selection pada Analisis Sentimen Review Film,” J. Intell. Syst., vol. 1, no. 1, pp. 55–59, 2015. [7] H. S. Ginting, K. M. Lhaksmana, and D. T. Murdiansyah, “Klasifikasi Sentimen Terhadap Bakal Calon Gubernur Jawa Barat 2018 di Twitter Menggunakan Naive Bayes,” vol. 5, no. 1, pp. 1793–1802, 2018. [8] N. Muchammad Shiddieqy Hadna, P. Insap Santosa, and W. Wahyu Winarno, “Studi Literatur Tentang Perbandingan Metode Untuk Proses Analisis Sentimen Di Twitter,” Semin. Nas. Teknol. Inf. dan Komun., no. March, pp. 2089–9815, 2016. [9] D. J. Haryanto, L. Muflikhah, and M. A. Fauzi, “Analisis Sentimen Review Barang Berbahasa Indonesia Dengan Metode Support Vector Machine Dan Query Expansion,” vol. 2, no. 9, pp. 2909–2916, 2018. [10] S. Rahmatullah, “Komparasi algoritma c4.5 dan svm berbasis particle swarm optimazation dalam penentuan kredit,” PARADIGMA, vol. XVIII, no. 1, pp. 79–87, 2016. [11] A. Salam et al., “ANALISIS SENTIMEN DATA KOMENTAR SOSIAL MEDIA FACEBOOK DENGAN K-NEAREST NEIGHBOR ( STUDI KASUS PADA AKUN JASA,” pp. 480–486, 2018. [12] A. Ali, “Sentiment Analysis on Twitter Data using KNN and SVM,” vol. 8, no. 6, pp. 19–25, 2017. [13] S. Dewi, “PADA PREDIKSI KEBERHASILAN PEMASARAN PRODUK LAYANAN PERBANKAN,” vol. XIII, no. 1, pp. 60–66, 2016. [14] A. D. L. James Clint, N. Dalia S., “PENGEMBANGAN PROGRAM APLIKASI SIMULASI UJIAN BERBASIS WEBSITE PADA SMA CANDRA NAYA,” 2018. [15] W. W. W. Nurrun Muchammad Shiddieqy Hadna, Paulus Insap Santosa, “STUDI LITERATUR TENTANG PERBANDINGAN METODE UNTUK PROSES ANALISIS SENTIMEN DI TWITTER,” vol. 2016, no. Sentika, pp. 18–19, 2016. [16] F. Imam and S. Azhari, “Proses Pemodelan Software Dengan Metode Waterfall Dan Extreme Programming : Studi,” 2008.
File :