Analisis Sentimen Data Tweet Menggunakan Model Jaringan Saraf Tiruan Dengan Pembobotan Delta Tf-idf

Authors

  • Chindy Amalia Telkomuniversity
  • Yuliant Sibaroni Telkomuniversity

DOI:

https://doi.org/10.34818/eoe.v7i2.12799

Abstract

Abstrak Kritik dan saran masyarakat Indonesia sangat berpengaruh untuk meningkatkan fasilitas dan kinerja pemerintah Indonesia. Salah satu media untuk menampung saran tersebut yaitu twitter dengan mengunggah tweet masyarakat dapat mengungkapkan keluh kesah mereka. Tetapi, dengan tweet yang berjumlah ratusan bahkan ribuan akan menyulitkan pemerintah untuk mengetahui kesimpulan dari seluruh data tweet. Data tweet yang diambil sebagai acuan yaitu data yang berisi tanggapan positif dan negatif dari masyarakat Indonesia. Oleh karena itu, penelitian ini mencoba menganalisis tweet mengenai sentimen masyarakat terhadap rencan perpindahan ibukota Indonesia. Analisis dilakukan dengan melakukan klasifikasi tweet yang berisi sentimen masyarakat terhadap rencana perpindahan ibukota Indonesia. Metode klasifikasi yang digunakan dalam penelitian ini adalah Jaringan Saraf Tiruan (JST) dengan model Multi Layer Perceptron yang dikombinasikan dengan fitur ekstraksi untuk dapat mendeteksi negasi dan pembobotan menggunakan Delta TF-IDF. Hasil pengujian pada aplikasi yang dibangun memperlihatkan bahwa akurasi memberikan tingkat akurasi yang cukup baik yaitu 67,75%. Kata kunci: Analisis sentimen, Jaringan Saraf Tiruan, Multi Layer Perceptron,TF-IDF, Delta TF-IDF Abstract Criticism and suggestions from the Indonesian people are very influential to improve the facilities and performance of the Indonesian government. One of the media to accommodate the suggestion is that Twitter by uploading community tweets can express their complaints. However, with tweets that number in the hundreds or even thousands it will be difficult for the government to find the conclusions from all tweet data. The tweet data taken as a reference is data that contains positive and negative responses from the people of Indonesia. Therefore, this study tries to analyze a tweet about community sentiment towards the planned move of the Indonesian capital. The analysis was carried out by classification of tweets containing public sentiments towards the planned move of the capital Indonesia. The classification method used in this study is the Artificial Neural Network (ANN) with a Multi Layer Perceptron model combined with extraction features to be able to detect negation and weighting using Delta TF-IDF. The test results on the application built show that accuracy gives a fairly good level of accuracy that is 67.75%. Keywords: sentiment analysis, artificial neural network, multi layer perceptron, TF-IDF, Delta TF-IDF

Downloads

Download data is not yet available.

References

[1] W. He, S. Zha, and L. Li, “Social media competitive analysis and text mining: A case study in the pizza industry,” Int. J. Inf. Manage., vol. 33, no. 3, pp. 464–472, 2013.

[2] S. A. Phand and J. A. Phand, “Twitter sentiment classification using stanford NLP,” Proc. - 1st Int. Conf. Intell. Syst. Inf. Manag. ICISIM 2017, vol. 2017-Janua, pp. 1–5, 2017.

[3] B. Liu, “LIBRO_NLP-handbook-sentiment-analysis,” pp. 1–38, 2010.

[4] N. Dwi Putranti and E. Winarko, “Analisis Sentimen Twitter untuk Teks Berbahasa Indonesia dengan Maximum Entropy dan Support Vector Machine,” IJCCS (Indonesian J. Comput. Cybern. Syst., vol. 8, no. 1, pp. 91–100, 2014.

[5] L. J. Handayani, D. Purwitasari, and A. Navastara, “Tweet Resolusi,” vol. 4, no. 1, 2015.

[6] T. Nasukawa and J. Yi, “Sentiment analysis: Capturing favorability using natural language processing,” Proc. 2nd Int. Conf. Knowl. Capture, K-CAP 2003, pp. 70–77, 2003.

[7] S. T. M. S. Dr. Suyanto, Data Mining. Informatika Bandung, 2017.

[8] J. LING, I. P. E. N. KENCANA, and T. B. OKA, “Analisis Sentimen Menggunakan Metode Naïve Bayes Classifier Dengan Seleksi Fitur Chi Square,” E-Jurnal Mat., vol. 3, no. 3, p. 92, 2014.

[9] Indriati and Ridok, “Sentiment analysis For Review Mobile Applications Using Neighbor Method Weighted K-Nearest Neighbor (NWKNN),” J. Environ. Eng. Sustain. Technol., 2016.

[10] A. Mustafa, A. Akbar, and A. Sultan, “Knowledge Discovery using Text Mining: A Programmable Implementation on Information Extraction and Categorization,” Int. J. Multimed. Ubiquitous Eng., vol. 4, no. 2, pp. 183–188, 2009.

[11] D. J. Haryanto, L. Muflikhah, and M. A. Fauzi, “Analisis Sentimen Review Barang Berbahasa Indonesia Dengan Metode Support Vector Machine Dan Query Expansion,” J. Pengemb. Teknol. Inf. dan Ilmu Komput. Univ. Brawijaya, vol. 2, no. 9, pp. 2909–2916, 2018.

[12] S. Asiyah and K. Fithriasari, “Klasifikasi Berita Online Menggunakan Metode Support Vector Machine Dan K-Nearest Neighbor,” J. Sains dan Seni ITS, vol. 5, no. 2, 2016.

[13] J. Martineau et al., “Delta TFIDF: An Improved Feature Space for Sentiment Analysis,” Proc. Second Int. Conf. Weblogs Soc. Media (ICWSM, vol. 29, no. May, pp. 490–497, 2008.

[14] J. Zhu, C. Xu, and H. S. Wang, “Sentiment classification using the theory of ANNs,” J. China Univ. Posts Telecommun., vol. 17, no. SUPPL. 1, pp. 58–62, 2010.

[15] D. Novitasari, “Klasifikasi Sinyal EEG Menggunakan Metode Fuzzy C-Means Clustering (FCM) Dan Adaptive Neighborhood Modified Backpropagation (ANMBP),” Mantik J. Mat., vol. 1, p. 31, Nov. 2015.

[16] E. Phil A. and G. Jim, “Application of Artificial Neural Network to Chromosome Classification,” Cytometry, vol. 14, pp. 627–639, 1993.

[17] H. Maier and G. Dandy, “Neural networks for the prediction and forecasting of water resources variables: A review of modelling issues and applications,” Environ. Model. Softw., vol. 15, pp. 101–124, Jan. 2000.

[18] R. Moraes, J. F. Valiati, and W. P. Gavião Neto, “Document-level sentiment classification: An empirical comparison between SVM and ANN,” Expert Syst. Appl., vol. 40, no. 2, pp. 621–633, 2013.

[19] P. I. Lesmana, “Analisis sentimen ..., Pekik Indra Lesmana, Fasilkom UI, 2013,” 2013.

[20] A. Achmad and A. A. Ilham, “Implementasi Algoritma Term Frequency – Inverse Document Frequency dan Vector Space Model untuk Klasifikasi Dokumen Naskah Dinas,” vol. 257, pp. 88–92, 2012.

[21] A. A. Maarif, “Penerapan Algoritma TF-IDF untuk Pencarian Karya Ilmiah,” Dok. Karya Ilm. | Tugas Akhir | Progr. Stud. Tek. Inform. - S1 | Fak. Ilmu Komput. | Univ. Dian Nuswantoro Semarang, no. 5, p. 4, 2015.

[22] Yusran, “IMPLEMENTASI JARINGAN SYARAF TIRUAN (JST) UNTUK MEMPREDIKSI HASIL NILAI UN MENGGUNAKAN METODE BACKPROPAGATION,” 2016.

[23] Y. D. Lestari, “Jaringan syaraf tiruan untuk prediksi penjualan jamur menggunakan algoritma backropagation,” J. ISD, vol. 2, no. 1, pp. 40–46, 2017.

[24] I. Menarianti, “Klasifikasi Data Mining Dalam Menentukan Pemberian Kredit Bagi Nasabah Koperasi,” Ilm. Teknosains, vol. 1, no. 1, pp. 36–45, 2015.

Downloads

Published

2020-08-01

Issue

Pages

7810-7820

Section

Program Studi S1 Informatika

How to Cite

Amalia, C., & Sibaroni, Y. (2020). Analisis Sentimen Data Tweet Menggunakan Model Jaringan Saraf Tiruan Dengan Pembobotan Delta Tf-idf. EProceedings of Engineering, 7(2), 7810-7820. https://doi.org/10.34818/eoe.v7i2.12799