Meningkatkan Akurasi Deteksi Berita Palsu dengan Pendekatan Berbasis Lexicon dan LSTM melalui Text Preprocessing dan Model Training

Edwin Hari Agus Prastyo, M Faisal

Abstract


Hoax news is an issue that is troubling the global community, including Indonesia. The spread of hoax news can cause various negative impacts, such as social division, public unrest, and can even endanger life safety. Hoaxes have become an epidemic in Indonesia, with 11,357 hoax issues identified by the Ministry of Communication and Information from August 2018 to March 2023. The combined approach of Lexicon-Based and LSTM results in improved accuracy in detecting hoax news. The combination of lexicon filters and pre-trained LSTM enables the model to identify hoax keywords and classify news with an accurate final score. Experimental results show that the use of Adam's optimizer produces high accuracy, achieving precision =1.0, recall=1.0, F1-score =1.0, and accuracy of 0.99. The model is able to perfectly distinguish between hoax and non-hoax news, demonstrating the effectiveness of using combined techniques and the right optimizer. However, there are some drawbacks that need to be considered, such as the reliance on a lexicon that may be incomplete and the potential for overfitting of the LSTM model. The results of this study provide insight into the importance of combined techniques in fake news detection, as well as the need for parameter adjustments and optimization strategies to minimize the drawbacks.

Keywords


Fake News Detection; Lexicon-Based; LSTM; Accuracy; Algorithm

Full Text:

PDF

References


P. Kominfo, “Siaran Pers No.150/HM/KOMINFO/07/2023 tentang Juni 2023, Kominfo Identifikasi 117 Konten Hoaks,†Juni 2023. [Online]. Available: “Siaran Pers No.150/HM/KOMINFO/07/2023 tentang Juni 2023, Kominfo Ihttps://www.kominfo.go.id/content/detail/50277/siaran-pers-no150hmkominfo072023-tentang-juni-2023-kominfo-identifikasi-117-konten-hoaks/0/siaran_pers.

J. Zhang, B. Dong dan P. S. Yu, “FakeDetector: Effective Fake News Detection With Deep Diffusive Neural Network,†2020.

B. Zaman, A. Justitia, K. N. Sani dan E. Purwanti, “An Indonesian Hoax News Detection System Using Reader Feedback and Naïve Bayes Algorithm,†Cybernetics and Information Technologies, 2020.

L. B. Hutama dan D. Suhartono, “Indonesian Hoax News Classification With Multilingual Transformer Model and BERTopic,†Informatica, 2022.

F. Prasetya dan F. Ferdiansyah, “Analisis Data Mining Klasifikasi Berita Hoax COVID 19 Menggunakan Algoritma Naive Bayes,†json, vol. 4, p. 132, 2022.

D. Armiady, “Analisis Metode DBSCAN (Density-Based Spatial Clustering of Application With Noise) Dalam Mendeteksi Data Outlier,†Jurikom (Jurnal Riset Komputer), 2022.

I. Baidawi, “Peranan Pemerintah Kabupaten Situbondo Dalam Menanggulangi Informasi Hoax,†Nusantara Journal of Islamic Studies, 2021.

S. V. Balshetwar, A. Rs dan D.J. R, “Fake news detection in social media based on sentiment analysis using classifier techniques,†Multimed Tools Appl, vol. 82, pp. 35781-35811, 2023.

U. P, A. Naik, S. Gurav, A. Kumar, C. S R dan M. B S, “Fake News Detection Using Neural Network,†IEEE International Conference on Integrated Circuits and Communication Systems (ICICACS), pp. 01-05, 2023.

M. A. Gohan, M. Andayan, M. Naufal dan M. Masliana, “Penyuluhan Penyebaran Covid-19 Dengan Pendekatan Participatory Action Research Dalam Menanggapi Berita Hoax Pada Media Sosial,†J-Ibm, vol. 1, pp. 66-73, 2021.

J. Pardede dan R. G. Ibrahim, “Implementasi Long Short-Term Memory untuk Identifikasi Berita Hoax Berbahasa Inggris pada Media Sosial,†J-Cosine, vol. 4, pp. 179-187, 2020.

M. Al-Shabi, “Evaluating the performance of the most important Lexicons used to Sentiment analysis and opinions Mining,†2020. [Online]. Available: https://api.semanticscholar.org/CorpusID:229705245.

F. R. Tama dan Y. Sibaroni, “Fake News (Hoaxes) Detection on Twitter Social Media Content through Convolutional Neural Network (CNN) Method,†jinav j. inf. vis, vol. 4, pp. 70-78, 2023.

H. R. Pulungan, “PERSPEKTIF MASYARAKAT MUSLIM ANGKOLA DALAM MENYIKAPI HOAX MELALUI PEMBELAJARAN PROSES MENTAL KOGNITIF,†paedagogik, vol. 13, pp. 1-23, 2022.

R. Yunanto, A. P. Purfuni dan A. Prabuwisesa, “Survei Literatur: Deteksi Berita Palsu Menggunakan Pendekatan Deep Learning,†jamika, vol. 11, pp. 118-130, 2021.

A. Khanifah dan A. M. Fauzi, “DAMPAK BERITA HOAX TENTANG COVID-19 TERHADAP PELAKSANAAN PROTOKOL KESEHATAN OLEH MASYARAKAT: (Studi Kasus Group Whatsapp Keluarga),†JIDS, vol. 6, pp. 250-267, 2022.

R. Saraswati, A. W. Nugroho dan R. Pasaribu, “Anti Hoax Movement For Students: Skills Training, Whole Person Education And Technology In Semarang City,†journal of information system, vol. 9, pp. 9-17, 2022.

Ni Made Ayu Juli Astari, D. G. H Divayana dan G. Indrawan, “Analisis Sentimen Dokumen Twitter Mengenai Dampak Virus Corona Menggunakan Metode Naive Bayes Classifier,†jurnal sistem dan informatika (jsi), 2020.

A. A. Kurniawan dan M. Mustikasari, “Implementasi Deep Learning Menggunakan Metode CNN Dan LSTM Untuk Menentukan Berita Palsu Dalam Bahasa Indonesia,†jurnal informatika universitas pamulang, 2021.

S. Hochreiter dan J. Schmidhuber, “Long Short-Term Memory,†Neural Computation, vol. 9, pp. 1735-1780, 1997.

F. Chollet, Deep learning with Python, New York: Manning Publications Co, 2018.

S. Senhaji, M. Hamlich dan M. Ouazzani Jamil, “Real time monitoring of water Quality using IoT and Deep learning,†E3S Web Conf, vol. 297, pp. 01-059, 2021.




DOI: https://doi.org/10.30865/mib.v8i3.7847

Refbacks

  • There are currently no refbacks.


Copyright (c) 2024 JURNAL MEDIA INFORMATIKA BUDIDARMA

Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 International License.


JURNAL MEDIA INFORMATIKA BUDIDARMA
Universitas Budi Darma
Secretariat: Sisingamangaraja No. 338 Telp 061-7875998
Email: mib.stmikbd@gmail.com

Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 International License.