Analisis Sentimen Ulasan Restoran Menggunakan Metode Support Vector Machine

Yoel Julianto(1*), Djoni Haryadi Setiabudi(2), Silvia Rostianingsih(3),


(1) Program Studi Teknik Informatika, Universitas Kristen Petra Surabaya
(2) Program Studi Teknik Informatika, Universitas Kristen Petra Surabaya
(3) Program Studi Teknik Informatika, Universitas Kristen Petra Surabaya
(*) Corresponding Author

Abstract


Reviews on restaurants on the internet have a huge impact on a restaurant. Reviews provided help other customers to evaluate the business or services provided from a  restaurant. Customers can leave positive or negative reviews. The large number of reviews from customers makes it difficult for restaurants to know if their restaurant has move positive or negative reviews. In this undergraduate thesis an application will be made to determine whether a restaurant has positive or negative reviews.

Application that is equipped with text mining features will help restaurant in evaluate their restaurant. The steps taken are preprocessing which consist of case folding, tokenization, stopword removal, and stemming. Then the process of converting text data into vector using TF-IDF. Furthermore the data will be trained using Support Vector Machine which later will generate a model that will be used to make predictions from input data. The data which be used as training are Indonesian-language reviews from various restaurants.

From this research conducted the result showed an accuracy of 93% and f1-score of 93%. To increase accuracy and f1-score values, classification model require TF-IDF parameters min_df  0.05, max_df  0.75, norm l2, n-gram (1, 2), linear SVM kernel with C 1. Besides TF-IDF and SVM parameters, the number of datasets can also increase confusion matrix and f1-score values.

Keywords


SVM; review; restaurant.

Full Text:

PDF

References


Coletta, L. F., da Silva, N. F., Hruschka, E. R., & Hruschka, E. R. 2014. Combining Classification and Clustering for Tweet Sentiment Analysis. Brazilian Conference on Intelligent Systems, 210 - 215.

Govindarajan, V., Anthony, R., Hartmann, F., Kraus, K., & Nilsson, G. 2013. EBOOK: Management Control Systems: European Edition. McGraw Hill.

Gunawan, D., Riana, D., Ardiansyah, D., Akbar, F., & Alfarizi, S. 2020. Komparasi Algoritma Support Vector Machine Dan Naive Bayes Dengan Algoritma Genetika Pada Analisis Sentimen Calon Gubernur Jabar 2018-2023. Jurnal Teknik Komputer AMIK BSI, VI(1), 121-129.

Han, J., & Kamber, M. 2006. Classification and prediction. Data mining: Concepts and techniques, 347-350.

Istijanto, M. M. 2005. Aplikasi Praktis Riset Pemasaran. Gramedia Pustaka Utama.

Lieaharyani, D. C. 2015. Automatic Essay Scoring System Using N-Gram and Cosine Similarity for Gamification Based E-Learning.

Maulina, D., & Sagara, R. 2018. Klasifikasi artikel hoax menggunakan support vector machine linear dengan pembobotan term frequency-Inverse document frequency. Jurnal Mantik Penusa, 2(1).

Melita, R., Amrizal, V., Suseno, H. B., & Dirjam, T. 2018. Penerapan Metode Term Frequency Inverse Document Frequency (Tf-Idf) Dan Cosine Similarity Pada Sistem Temu Kembali Informasi Untuk Mengetahui Syarah Hadits Berbasis Web (Studi Kasus: Syarah Umdatil Ahkam). Jurnal Teknik Informatika, 11(2), 149-164.

Muthia, D. A. 2017. Analisis Sentimen Pada Review Restoran Dengan Teks Bahasa Indonesia Mengunakan Algoritma Naive Bayes. Jurnal Ilmu Pengetahuan dan Teknologi Komputer, 39-45.

Nasukawa, T., & Yi, J. 2003. Sentiment Analysis: Capturing Favorability Using Natural Language Processing. In Proceedings of the 2nd International Conference on Knowledge Capture, 70 - 77.

Ningrum, H. C. 2018. Perbandingan Metode Support Vector Machine (SVM) Linear, Radial Basis Function (RBF), dan Polinomial Kernel Dalam Klasifikasi Bidang Studi Lanjut Piliihan Alumni UII.

Patel, S. 2018. Chapter 2 : SVM (Support Vector Machine) — Theory. Retrieved from Medium: https://medium.com/machine-learning-101/chapter-2-svm-support-vector-machine-theory-f0812effc72

Permadi, V. A. 2002. Analisis Sentimen Menggunakan Algoritma Naive Bayes Terhadap Review Restoran di Singapura. Jurnal Buana Informatika, 11(2), 141-151.

Pustejovsky, J., & Stubbs, A. 2012. Natural Language Annotaion for Machine Learning: A guide to corpus-building for application. O'Reilly Media, Inc.

Rachman, F., & S. W., P. 2012. Perbandingan Klasifikasi Tingkat Keganasan Breast Cancer Dengan Menggunakan Regresi Logistik Ordinal Dan Support Vector Machine (SVM).

Santoso, B. 2007. Data Mining Teknik Pemanfaatan Untuk Keperluan Bisnis. Yogyakarta: Graha Ilmu.

Siagian, R. Y. 2011. Klasifikasi Parket Kayu Jati Menggunakan Metode Support Vector Machine (SVM).

Walker, J. R., & Lundberg, D. E. 2005. The restaurant: from concept to operation (4th ed.). Hoboken: Wiley.

Wang, H., & Hu, D. 2005. Comparison of SVM and LS-SVM for Regression. International Conference on Neural Network and Brain, 279 - 283.

Zhang, Z., Ye, Q., Zhang, Z., & Li, Y. 2011. Sentiment classification of Internet restaurant reviews written in Cantonese. Expert Systems with Applications, 38(6), 7674-7682.


Refbacks

  • There are currently no refbacks.


Jurnal telah terindeks oleh :