Hoax Detection Using Long Short-Term Memory (LSTM) and Gate Recurrent Unit (GRU) on Social Media
-
Dion Pratama Putra
*
Telkom University, Bandung,
Indonesia
- Erwin Budi Setiawan Telkom University, Bandung, Indonesia (*) Corresponding Author
Abstract
There are negative effects of the ease of obtaining information in today's society, one of which is the rise of hoaxes on the internet. As much as 92.40% of social media platforms such as Twitter are used to spread hoaxes. Launched on July 13, 2006, Twitter is a microblogging service where users can spread information at no cost to themselves or others. In this study, the authors will conduct hoax news detection on Twitter social media using the Long Short - Term Memory (LSTM) method and Gate Recurent Unit (GRU) and gloVe feature expansion. with a dataset of 25,234 data which produces accuracy results in TF-IDF on each model, namely 97.33% in LSTM and 96.75% in GRU, and an increase in accuracy of 0.22% in the tweet corpus on LSTM and an increase in accuracy of 0.15 in the BeritaTweet corpus on GRU.
Downloads
References
M. P. Utami, O. D. Nurhayati, and B. Warsito, “Hoax Information Detection System Using Apriori Algorithm and Random Forest Algorithm in Twitter,” in 6th International Conference on Interactive Digital Media, ICIDM 2020, Dec. 2020. doi: 10.1109/ICIDM51048.2020.9339648.
C. Juditha, “Interaksi Komunikasi Hoax di Media Sosial serta Antisipasinya Hoax Communication Interactivity in Social Media and Anticipation,” 2018.
A. Fauzi, E. B. Setiawan, and Z. K. A. Baizal, “Hoax News Detection on Twitter using Term Frequency Inverse Document Frequency and Support Vector Machine Method,” in Journal of Physics: Conference Series, May 2019, vol. 1192, no. 1. doi: 10.1088/1742-6596/1192/1/012025.
B. P. Nayoga, R. Adipradana, R. Suryadi, and D. Suhartono, “Hoax Analyzer for Indonesian News Using Deep Learning Models,” in Procedia Computer Science, 2021, vol. 179, pp. 704–712. doi: 10.1016/j.procs.2021.01.059.
F. Rahutomo, I. Y. R. Pratiwi, and D. M. Ramadhani, “Eksperimen Naïve Bayes Pada Deteksi Berita Hoax Berbahasa Indonesia,” JURNAL PENELITIAN KOMUNIKASI DAN OPINI PUBLIK, vol. 23, no. 1, Jul. 2019, doi: 10.33299/jpkop.23.1.1805.
K. Shu, L. Cui, S. Wang, D. Lee, and H. Liu, “Defend: Explainable fake news detection,” in Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Jul. 2019, pp. 395–405. doi: 10.1145/3292500.3330935.
E. Utami, A. F. Iskandar, W. Hidayat, A. B. Prasetyo, and A. D. Hartanto, “Covid-19 Hoax Detection Using KNN in Jaccard Space,” IJCCS (Indonesian Journal of Computing and Cybernetics Systems), vol. 15, no. 3, p. 255, Jul. 2021, doi: 10.22146/ijccs.67392.
C. S. Sriyano and E. B. Setiawan, “Pendeteksian Berita Hoax Menggunakan Naive Bayes Multinomial Pada Twitter dengan Fitur Pembobotan TF-IDF.”
J. Eka Sembodo, E. Budi Setiawan, and Z. Abdurahman Baizal, “Data Crawling Otomatis pada Twitter,” Sep. 2016, pp. 11–16. doi: 10.21108/indosc.2016.111.
Y. T. Zhang, L. Gong, and Y. C. Wang, “Improved TF-IDF approach for text classification,” J Zhejiang Univ Sci, vol. 6 A, no. 1, pp. 49–55, Jan. 2005, doi: 10.1631/jzus.2005.A0049.
A. Nurdin, B. Anggo, S. Aji, A. Bustamin, and Z. Abidin, “PERBANDINGAN KINERJA WORD EMBEDDING WORD2VEC, GLOVE, DAN FASTTEXT PADA KLASIFIKASI TEKS,” Jurnal TEKNOKOMPAK, vol. 14, no. 2, p. 74, 2020.
A. Aizawa, “An information-theoretic perspective of tf-idf measures q.” [Online]. Available: www.elsevier.com/locate/infoproman
J. Pennington, R. Socher, and C. D. Manning, “GloVe: Global Vectors for Word Representation.” [Online]. Available: http://nlp.
st Alfiyah Ramadian Jamaludin, “Deteksi Berita Hoax di Media Sosial Twitter dengan Ekspansi Fitur Menggunakan Glove.”
“Abstract Keywords-traffic flow prediction; LSTM; GRU; ARIMA A. Parameter Models.”
A. Khumaidi, R. Raafi, I. Permana Solihin, and J. Rs Fatmawati, “Pengujian Algoritma Long Short Term Memory untuk Prediksi Kualitas Udara dan Suhu Kota Bandung,” Jurnal Telematika, vol. 15, no. 1.
A. Hanifa, S. A. Fauzan, M. Hikal, and M. B. Ashfiya, “PERBANDINGAN METODE LSTM DAN GRU (RNN) UNTUK KLASIFIKASI BERITA PALSU BERBAHASA INDONESIA COMPARISON OF LSTM AND GRU (RNN) METHODS FOR FAKE NEWS CLASSIFICATION IN INDONESIAN.” [Online]. Available: https://covid19.go.id/p/hoax-buster.
B. P. Nayoga, R. Adipradana, R. Suryadi, and D. Suhartono, “Hoax Analyzer for Indonesian News Using Deep Learning Models,” in Procedia Computer Science, 2021, vol. 179, pp. 704–712. doi: 10.1016/j.procs.2021.01.059.
V. M. Patro and M. Ranjan Patra, “Augmenting Weighted Average with Confusion Matrix to Enhance Classification Accuracy,” Transactions on Machine Learning and Artificial Intelligence, vol. 2, no. 4, Aug. 2014, doi: 10.14738/tmlai.24.328.
X. Deng, Q. Liu, Y. Deng, and S. Mahadevan, “An improved method to construct basic probability assignment based on the confusion matrix for classification problem,” Inf Sci (N Y), vol. 340–341, pp. 250–261, May 2016, doi: 10.1016/j.ins.2016.01.033.
Bila bermanfaat silahkan share artikel ini
Berikan Komentar Anda terhadap artikel Hoax Detection Using Long Short-Term Memory (LSTM) and Gate Recurrent Unit (GRU) on Social Media
Pages: 1815−1820
Copyright (c) 2023 Dion Pratama Putra, Erwin Budi Setiawan
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under Creative Commons Attribution 4.0 International License that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (Refer to The Effect of Open Access).
