Sentiment Analysis from Indonesian Twitter Data Using Support Vector Machine And Query Expansion Ranking

Hasbi Atsqalani; Nur Hayatin; Christian Sri Kusuma Aditya

doi:10.15575/join.v7i1.669

Sentiment Analysis from Indonesian Twitter Data Using Support Vector Machine And Query Expansion Ranking

Hasbi Atsqalani, Nur Hayatin, Christian Sri Kusuma Aditya

Abstract

Sentiment analysis is a computational study of a sentiment opinion and an overflow of feelings expressed in textual form. Twitter has become a popular social network among Indonesians. As a public figure running for president of Indonesia, public opinion is very important to see and consider the popularity of a presidential candidate. Media has become one of the important tools used to increase electability. However, it is not easy to analyze sentiments from tweets on Twitter apps, because it contains unstructured text, especially Indonesian text. The purpose of this research is to classify Indonesian twitter data into positive and negative sentiments polarity using Support Vector Machine and Query Expansion Ranking so that the information contained therein can be extracted and from the observed data can provide useful information for those in need. Several stages in the research include Crawling Data, Data Preprocessing, Term Frequency – Inverse Document Frequency (TF-IDF), Feature Selection Query Expansion Ranking, and data classification using the Support Vector Machine (SVM) method. To find out the performance of this classification process, it will be entered into a configuration matrix. By using a discussion matrix, the results show that calcification using the proposed reached accuracy and F-measure score in 77% and 68% respectively.

Keywords

Sentiment analysis; Support vector machine; Query expansion ranking; Social media data

Full Text:

PDF

References

O. C. WEBSINDO, “INDONESIA DIGITAL 2019 MEDIA SOSIAL,” 2019. .

R. C. Chen and C. H. Hsieh, “Web page classification based on a support vector machine using a weighted vote schema,” Expert Syst. Appl., vol. 31, no. 2, pp. 427–435, 2006, doi: 10.1016/j.eswa.2005.09.079.

N. D. Mentari, M. A. Fauzi, and L. Muflikhah, “Analisis Sentimen Kurikulum 2013 Pada Sosial Media Twitter Menggunakan Metode K-Nearest Neighbor dan Feature Selection Query Expansion Ranking,” J. Pengemb. Teknol. Inf. dan Ilmu Komput. Univ. Brawijaya, vol. 2, no. 8, pp. 2739–2743, 2018.

Anwar, M. Y. (2019). Klasifikasi Halaman Web Untuk Anak Menggunakan Metode Weighted Voting Support Vector Machine.

R. Adhitia and A. Purwarianti, “Penilaian Esai Jawaban Bahasa Indonesia Menggunakan Metode Svm - Lsa Dengan Fitur Generik,” J. Sist. Inf., vol. 5, no. 1, p. 33, 2012.

Arifin, A. Z., Mahendra, I. P. A. K., & Ciptaningtyas, H. T. (2009). Enhanced confix stripping stemmer and ants algorithm for classifying news document in indonesian language. In The International Conference on Information & Communication Technology and Systems (Vol. 5, pp. 149-158).

H. Himawan, W. Kaswidjanti, A. Sentimen, M. Sosial, and L. Based, “Metode Lexicon Based Dan Support Vector Machine Untuk Menganalisis Sentimen Pada Media Sosial Sebagai Rekomendasi Oleh-Oleh Favorit,” vol. 2018, no. November, pp. 235–244, 2018.

T. Parlar and S. A. Ozel, “A new feature selection method for sentiment analysis of Turkish reviews,” Proc. 2016 Int. Symp. Innov. Intell. Syst. Appl. INISTA 2016, no. December 2017, 2016, doi: 10.1109/INISTA.2016.7571833.

H. P. P. R. Zuriel and A. Fahrurozi, “Implementasi Algoritma Klasifikasi Support Vector Machine Untuk Analisa Sentimen Pengguna Twitter Terhadap Kebijakan Psbb,” J. Ilm. Inform. Komput., vol. 26, no. 2, pp. 149–162, 2021.

R. Adhitia and A. Purwarianti, “Penilaian Esai Jawaban Bahasa Indonesia Menggunakan Metode Svm - Lsa Dengan Fitur Generik,” J. Sist. Inf., vol. 5, no. 1, p. 33, 2012, doi: 10.21609/jsi.v5i1.260.