Analisis Sentimen untuk Identifikasi Bantuan Korban Bencana Alam berdasarkan Data di Twitter Menggunakan Metode K-Means dan Naive Bayes

Penulis

  • Vincentius Riandaru Prasetyo Universitas Surabaya, Surabaya
  • Gatum Erlangga Universitas Surabaya, Surabaya
  • Delta Ardy Prima Universitas Surabaya, Surabaya

DOI:

https://doi.org/10.25126/jtiik.20231057077

Abstrak

Media sosial telah menjadi sarana yang umum bagi orang untuk mengekspresikan diri dan meminta bantuan ketika mereka mengalami musibah. Banyak korban bencana alam di Indonesia menggunakan Twitter untuk meminta bantuan seperti makanan, air bersih, dan lainnya. Penelitian ini bertujuan untuk melakukan analisis sentimen dari data Twitter untuk menentukan bantuan bagi korban bencana alam di Indonesia. Pada penelitian ini, metode K-Means dan Naïve Bayes dikombinasikan untuk melakukan analisis sentimen. Dalam penelitian ini, bantuan yang akan ditemukan adalah pakaian, makanan, air bersih, dan obat. Metode K-Means dipilih karena mudah digunakan dan mudah diimplementasikan, sementara metode Naïve Bayes digunakan karena menghasilkan nilai akurasi yang baik dalam klasifikasi. Hasil uji coba memperlihatkan bahwa kombinasi K-Means dan Naïve Bayes menghasilkan akurasi sebesar 76,46%, di mana akurasi tersebut lebih tinggi daripada implementasi Naïve Bayes saja, dengan akurasi sebesar 74,65%. Berdasarkan validasi yang dilakukan dengan Kepala Badan Penanggulangan Bencana Daerah (BPBD) di Kota Tarakan, sistem ini dapat membantu BPBD Kota Tarakan dalam memberikan bantuan yang tepat ke lokasi bencana.

 

Abstract

 

Social media has become a common place for people to express themselves and ask for help when they are going through a calamity. Many victims of natural disasters in Indonesia use Twitter to request assistance such as food, clean water, and others. Therefore, this study aims to conduct sentiment analysis from Twitter data to determine aid for victims of natural disasters in Indonesia. In this research, K-Means and Naïve Bayes methods will be combined for sentiment analysis. In this study, the assistance that will be found is clothing, food, clean water, and medicine. The K-Means method was chosen because it is easy to use and easy to implement, while the Naïve Bayes method was chosen because it has a good level of accuracy in classification. The results showed that the combination of K-Means and Naïve Bayes had a higher accuracy rate of 76.46%, compared to the use of Naïve Bayes alone, which was 74.65%. Based on the validation conducted with the Head of the Regional Disaster Management Agency (BPBD) in Tarakan City, this system can assist the Tarakan City BPBD in providing appropriate assistance to disaster locations.

Downloads

Download data is not yet available.

Referensi

ABBAS, M., ALI, K., JAMALI, A. A., MEMON, S. DAN AHMED, A., 2019. Multinomial Naive Bayes Classification Model for Sentiment Analysis. International Journal of Computer Science and Network Security, 19(3), pp. 62-67.

BEIGI, G., HU, X., MACIEJEWSKI, R. dan LIU, H., 2016. An Overview of Sentiment Analysis in Social Media and Its Applications in Disaster Relief. Sentiment Analysis and Ontology Engineering, Volume 639, pp. 313-340.

BIRJALI, M., KASRI, M. dan HSSANE, A. B., 2021. A comprehensive survey on sentiment analysis: Approaches, challenges and trends. Knowledge-Based Systems, Volume 226.

DANG, N. C., MORENO-GARCÍA, M. dan PRIETA, F. D. L., 2020. Sentiment Analysis Based on Deep Learning: A Comparative Study. Electronics, Volume 9, pp. 1-29.

GUNAWAN, R., RAHMATULLOH, A., DARMAWAN, I. dan FIRDAUS, F., 2018. Comparison of Web Scraping Techniques : Regular Expression, HTML DOM and Xpath. Yogyakarta, Atlantis Press.

HAKIM, L., 2019. Kerangka Kerja Kesiapan Menghadapi Bencana. Jurnal Dialog Penanggulangan Bencana , 10(1), pp. 1-11.

JIMMY dan PRASETYO, V. R., 2021. Sentiment Analysis on Feedback of Higher Education Teaching Conduct An Empirical Evaluation of Methods. Surabaya, AIP Publishing.

JUNG, K., BAE, D. H., UM, M. J., KIM, S., JEON, S. DAN PARK, D., 2020. Evaluation of Nitrate Load Estimations Using Neural Networks and Canonical Correlation Analysis with K-Fold Cross-Validation. Sustainability, 12(1), pp. 1-17.

KARAMI, A., SHAH, V., VAEZI, R. dan BANSAL, A., 2020. Twitter speaks: A case of national disaster situational awareness. Journal of Information Science, 46(3), pp. 313-324.

KATADATA, 2019. Databooks. [Online]

Available at: https://databoks.katadata.co.id/datapublish/2019/02/08/berapa-pengguna-media-sosial-indonesia

[Accessed 15 Januari 2023].

LI, H., CARAGEA, D., CARAGEA, C. dan HERNDON, N., 2018. Disaster response aided by tweet classification with a domain adaptation approach. Journal of Contingencies and Crisis Management, Volume 26, pp. 16-27.

MUPPIDI, S., RAO, P. S. dan MURTHY, M. R. K., 2019. Identification of Natural Disaster Affected Area Using Twitter. Advances in Decision Sciences, Image Processing, Security and Computer Vision, Volume 1, pp. 792-801.

NEGARA, A. B. P., MUHARDI, H. dan PUTRI, I. M., 2020. Analisis Sentimen Maskapai Penerbangan Menggunakan Metode Naive Bayes Dan Seleksi Fitur Information Gain. Jurnal Teknologi Informasi dan Ilmu Komputer, 7(3), pp. 599-606.

ORKPHOL, K. dan YANG, W., 2019. Sentiment Analysis on Microblogging with K-Means Clustering and Artificial Bee Colony. International Journal of Computational Intelligence and Applications, 18(3).

PATEL, S. P. dan UPADHYAY, S. H., 2020. Euclidean distance based feature ranking and subset selection for bearing fault diagnosis. Expert Systems With Applications, Volume 154, pp. 1-16.

PRASETYO, V. R., 2018. Searching cheapest product on three different e-commerce using k-means algorithm. Bali, IEEE Xplore.

PRASETYO, V. R., AXEL, S., SOEBROTO, J. T., SUGIARTO, D., WINATAN, S. A. DAN NJUDANG, S. D., 2022. Prediksi Harga Emas Berdasarkan Data gold.org menggunakan Metode Long Short Term Memory. Jurnal SISTEMASI, 11(3), pp. 623-629.

PRASETYO, V. R., HARTANTO, B. dan MULYONO, A. A., 2019. Penentuan Pembimbing Tugas Akhir Mahasiswa Jurusan Teknik Informatika Universitas Surabaya Dengan Metode Dice Coefficient. Jurnal TEKNIKA, 8(1), pp. 44-51.

PRASETYO, V. R., MIRANTI, F. A. dan LIMANTO, S., 2022. Implementation of Feature Selection to Reduce the Number of Features in Determining the Initial Centroid of K-Means Algorithm. Yogyakarta, IEEE Xplore.

PRASETYO, V. R. dan SAMUDRA, A. H., 2021. Hate speech content detection system on Twitter using K-nearest neighbor method. Surabaya, AIP Publishing.

PRASETYO, V. R., WIDIASRI, M. dan ANGKIRIWANG, M. M., 2022. Sistem Berbasis Web Untuk Koreksi Soal Esai Dengan Association Rules. Jurnal TEKNIKA, 11(1), pp. 62-68.

RAMADHAN, N. G. dan ADHINATA, F. D., 2022. Sentiment analysis on vaccine COVID-19 using word count and Gaussian Naïve Bayes. Indonesian Journal of Electrical Engineering and Computer Science, 26(3), pp. 1765-1772.

RAMDUGE, K. D. dan RAJHANS, N. R., 2023. K-means clustering for optimization of spare parts delivery. Management Science Letters, 13, pp. 235-240.

ROSYIDA, A., NURMASARI, R. dan SUPRAPTO, 2019. Analisis Perbandingan Dampak Kejadian Bencana Hidrometeorologi Dan Geologi Di Indonesia Dilihat Dari Jumlah Korban Dan Kerusakan (Studi: Data Kejadian Bencana Indonesia 2018). Jurnal Dialog Penanggulangan Bencana, 10(1), pp. 12-21.

RUZ, G. A., HENRIQUEZ, P. A. dan MASCARENO, A., 2020. Sentiment analysis of Twitter data during critical events through Bayesian networks classifiers. Future Generation Computer Systems, Volume 106, pp. 92-104.

SUARANTB, 2019. SUARANTB.com. [Online]

Available at: https://www.suarantb.com/2019/05/08/ratusan-juta-bantuan-gempa-di-lobar-diduga-salah-sasaran/

[Accessed 15 Januari 2023].

XU, H., YAO, S., LI, Q. dan YE, Z., 2020. An Improved K-means Clustering Algorithm. Dortmund, IEEE Explore.

ZUL, M. I., YULIA, F. dan NURMALASATI, D., 2018. Social Media Sentiment Analysis Using K-Means and Naïve Bayes Algorithm. Batam, IEEE Explore.

Diterbitkan

17-10-2023

Terbitan

Bagian

Ilmu Komputer

Cara Mengutip

Analisis Sentimen untuk Identifikasi Bantuan Korban Bencana Alam berdasarkan Data di Twitter Menggunakan Metode K-Means dan Naive Bayes. (2023). Jurnal Teknologi Informasi Dan Ilmu Komputer, 10(5), 1055-1062. https://doi.org/10.25126/jtiik.20231057077