Performance comparison of support vector machine (SVM) with linear kernel and polynomial kernel for multiclass sentiment analysis on twitter


Rifqatul Mukarramah(1*); Dedy Atmajaya(2); Lutfi Budi Ilmawan(3);

(1) Universitas Muslim Indonesia
(2) Universitas Muslim Indonesia
(3) Universitas Muslim Indonesia
(*) Corresponding Author

  

Abstract


Sentiment analysis is a technique to extract information of ones perception, called sentiment, on an issue or event. This study employs sentiment analysis to classify societys response on covid-19 virus posted at twitter into 4 polars, namely happy, sad, angry, and scared. Classification technique used is support vector machine (SVM) method which compares the classification performance figure of 2 linear kernel functions, linear and polynomial. There were 400 tweet data used where each sentiment class consists of 100 data. Using the testing method of k-fold cross validation, the result shows the accuracy value of linear kernel function is 0.28 for unigram feature and 0.36 for trigram feature. These figures are lower compared to accuracy value of kernel polynomial with 0.34 and 0.48 for unigram and trigram feature respectively. On the other hand, testing method of confusion matrix suggests the highest performance is obtained by using kernel polynomial with accuracy value of 0.51, precision of 0.43, recall of 0.45, and f-measure of 0.51.

Keywords


SVM Algorithm; Covid-19; Linear Kernels; Polynomial Kernels; Sentiment Analysis

  
  

Full Text:

PDF
  

Article Metrics

Abstract view: 885 times
PDF view: 327 times
     

Digital Object Identifier

doi  https://doi.org/10.33096/ilkom.v13i2.851.168-174
  

Cite

References


W. A. F. Dewi, Dampak COVID-19 terhadap Implementasi Pembelajaran Daring di Sekolah Dasar, Edukatif J. Ilmu Pendidik., vol. 2, no. 1, pp. 5561, 2020.

D. Telaumbanua, Urgensi Pembentukan Aturan Terkait Pencegahan Covid-19 di Indonesia, QALAMUNA J. Pendidikan, Sos. dan Agama, vol. 12, no. 01, pp. 5970, 2020.

M. Siahaan, Dampak Pandemi Covid-19 Terhadap Dunia Pendidikan, J. Kaji. Ilm., vol. 1, no. 1, pp. 7380, 2020.

A. Syahadati, N. C. Lengkong, O. Safitri, S. Machsus, Y. R. Putra, and R. Nooraeni, ANALISIS SENTIMEN PENERAPAN PSBB DI DKI JAKARTA DAN DAMPAKNYA TERHADAP PERGERAKAN IHSG, vol. 15, no. 1, pp. 2025, 2021.

R. Nuraini, No Title, indonesia.go.id. 2020.

R. Habibi, D. B. Setyohadi, and E. Wati, Analisis Sentimen Pada Twitter Mahasiswa Menggunakan Metode Backpropagation, J. Inform., vol. 12, no. 1, 2016.

A. V. Sudiantoro and E. Zuliarso, Analisis Sentimen Twitter Menggunakan Text Mining Dengan Algoritma NAVE BAYES CLASSIFIER, Pros. SINTAK 2018, pp. 398401, 2018.

L. Budi and A. Mude, Perbandingan Metode Klasifikasi Support Vector Machine dan Nave Bayes untuk Analisis Sentimen pada Ulasan Tekstual di Google Play Store, vol. 12, no. 2, pp. 154161, 2020.

N. Hafidz, S. Anggraeni, and W. Gata, Sentimen Analisis Informasi Covid-19 menggunakan Support Vector Machine dan Nave Bayes, 2019.

F. Sodik and I. Kharisudin, Analisis Sentimen dengan SVM , NAIVE BAYES dan KNN untuk Studi Tanggapan Masyarakat Indonesia Terhadap Pandemi Covid-19 pada Media Sosial Twitter, vol. 4, pp. 628634, 2021.

H. Azis et al., Analisis Perbandingan Performa Metode Klasifikasi pada Dataset Multiclass Citra Busur Panah, vol. 19, no. 3, pp. 286294, 2020.

M. S. Hadna, P. I. Santosa, and W. W. Winarno, Studi Literatur Tentang Perbandingan Metode Untuk Proses Analisis Sentimen Di Twitter, Semin. Nas. Teknol. Inf. dan Komun., vol. 2016, no. Sentika, pp. 5764, 2016.

S. Sharma, S. Srivastava, A. Kumar, and A. Dangi, Multi-Class Sentiment Analysis Comparison Using Support Vector Machine ( SVM ) and BAGGING Technique An Ensemble Method, 2018 Int. Conf. Smart Comput. Electron. Enterp., no. February 2019, pp. 16, 2018.

N. B. N-gram, I. Pujadayanti, M. A. Fauzi, and Y. A. Sari, Prediksi Rating Otomatis pada Ulasan Produk Kecantikan dengan Metode Prediksi Rating Otomatis pada Ulasan Produk Kecantikan dengan Metode Nave Bayes dan N-gram, no. November, 2018.

D. H. Wahid and A. SN, Peringkasan Sentimen Esktraktif di Twitter Menggunakan Hybrid TF-IDF dan Cosine Similarity, IJCCS (Indonesian J. Comput. Cybern. Syst., vol. 10, no. 2, p. 207, 2016.


Refbacks

  • There are currently no refbacks.


Copyright (c) 2021 Rifqatul Mukarramah, Dedy Atmajaya, Lutfi Budi Ilmawan

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