Implementation of BiLSTM-SVM Algorithm to Detect Fake News on Text-Based Media
DOI:
https://doi.org/10.24014/coreit.v9i2.18982Keywords:
BiLSTM-SVM, Fake News, Online media, TensorFlow, Twitter,Abstract
Online media is one of the places where news can spread quickly and everyone can access it easily and freely. Not only real or valid news is spread on online media, but fake news can also be easily spread on online media, and readers sometimes do not realize that the news they read is fake. As a result, wrong opinions arise that can lead to disputes, as well as divisions between individuals or groups. This study implements the BiLSTM-SVM algorithm to detect fake news that is spread on one of the online media, namely Twitter. The steps taken are tidying up the news text (text preprocessing), converting every word from the news text into numbers in vector form (word embedding), processing the numbers, and then classifying the results of the processing with the BiLSTM-SVM model formed with TensorFlow 2.0 help, and see the performance generated by the BiLSTM-SVM algorithm. The results obtained include an accuracy rate of 86% and an F1 Score value of 87.5% in detecting news from data validation with the same news topic.
References
C. Juditha, “Interaksi Komunikasi Hoax di Media Sosial Serta Antisipasinya,” J. Pekommas, vol. 3, no. 1, pp. 31–34, 2018.
D. Susilawati and W. D. Putri, “Begini Dampak Berita Hoax | Republika Online,” 2017. https://www.republika.co.id/berita/trendtek/internet/17/04/11/oo7uxj359-begini-dampak-berita-hoax (accessed Nov. 02, 2021).
Jasmi, “Mengenal Ciri-ciri Berita Hoax dan Dampaknya | QuBisa,” 2021. https://www.qubisa.com/article/ciri-ciri-dan-dampak-hoax#showContent (accessed Feb. 25, 2022).
B. Agung, “Saat Hoaks yang Dibuat Makin Canggih, Kecerdasan Buatan Jadi Harapan Melawannya,” 2019. https://dailysocial.id/post/saat-hoaks-yang-dibuat-makin-canggih-kecerdasan-buatan-jadi-harapan-melawannya (accessed Nov. 07, 2021).
K. Barkved, “How To Know if Your Machine Learning Model Has Good Performance | Obviously AI,” 2022. https://www.obviously.ai/post/machine-learning-model-performance (accessed Aug. 05, 2022).
J. Fourati, M. Othmani, and H. Ltifi, “A hybrid model based on bidirectional long-short term memory and support vector machine for rest tremor classification,” Signal, Image Video Process., no. March, 2022, doi: 10.1007/s11760-022-02180-9.
P. S. Reddy, D. Elizabeth Roy, P. Manoj, M. Keerthana, and P. V. Tijare, “A study on fake news detection using naïve bayes, SVM, neural networks and LSTM,” J. Adv. Res. Dyn. Control Syst., vol. 11, no. 6 Special Issue, pp. 942–947, 2019.
A. Y. Triartanto, “Kredibilitas Teks Hoax Di Media Siber,” J. Komun., vol. 6, no. 2, pp. 33–36, 2015, [Online]. Available: http://ejournal.bsi.ac.id/ejurnal/index.php/jkom/article/view/2464/1700.
M. Zulfikar, “Hoaks Masih Laku di Pasaran, Berikut 4 Ciri Hoaks Menurut Kominfo - National Geographic,” 2019. https://nationalgeographic.grid.id/read/131824796/hoaks-masih-laku-di-pasaran-berikut-4-ciri-hoaks-menurut-kominfo (accessed Mar. 25, 2022).
A. Cimino and F. Dell’Orletta, “Tandem LSTM-SVM approach for sentiment analysis,” CEUR Workshop Proc., vol. 1749, 2016, doi: 10.4000/books.aaccademia.2003.
A. Graves, S. Fernández, and J. Schmidhuber, “Bidirectional LSTM networks for improved phoneme classification and recognition,” Lect. Notes Comput. Sci. (including Subser. Lect. Notes Artif. Intell. Lect. Notes Bioinformatics), vol. 3697 LNCS, pp. 799–804, 2005, doi: 10.1007/11550907_126.
E. Zvornicanin, “Differences Between Bidirectional and Unidirectional LSTM | Baeldung on Computer Science,” 2022. https://www.baeldung.com/cs/bidirectional-vs-unidirectional-lstm (accessed May 21, 2022).
R. Dwi, W. Santosa, M. A. Bijaksana, and A. Romadhony, “Implementasi Algoritma Long Short-Term Memory ( LSTM ) untuk Mendeteksi Penggunaan Kalimat Abusive Pada Teks Bahasa Indonesia,” J. Tugas Akhir Fak. Inform., vol. 8, no. 1, pp. 691–702, 2021.
R. Aggarwal, “Bi-LSTM. What is a neural network? Just like our… | by Raghav Aggarwal | Medium,” 2019. https://medium.com/@raghavaggarwal0089/bi-lstm-bc3d68da8bd0 (accessed Mar. 29, 2022).
Z. Cui, R. Ke, Z. Pu, and Y. Wang, “Deep Bidirectional and Unidirectional LSTM Recurrent Neural Network for Network-wide Traffic Speed Prediction,” pp. 1–11, 2018, [Online]. Available: http://arxiv.org/abs/1801.02143.
N. S. Kiruthika and G. Thailambal, “Dynamic Light Weight Recommendation System for Social Networking Analysis Using a Hybrid LSTM-SVM Classifier Algorithm,” Opt. Mem. Neural Networks, vol. 31, no. 1, pp. 59–75, 2022, doi: 10.3103/s1060992x2201009x.
U. Verma, “Text Preprocessing for NLP (Natural Language Processing),Beginners to Master | by Ujjawal Verma | Analytics Vidhya | Medium,” 2020. https://medium.com/analytics-vidhya/text-preprocessing-for-nlp-natural-language-processing-beginners-to-master-fd82dfecf95 (accessed May 21, 2022).
D. Yadav, “NLP: Building Text Cleanup and PreProcessing Pipeline | by Dinesh Yadav | Towards Data Science,” 2020. https://towardsdatascience.com/nlp-building-text-cleanup-and-preprocessing-pipeline-eba4095245a0 (accessed Apr. 29, 2022).
K. Rastogi, “Text Cleaning Methods in NLP - Analytics Vidhya,” 2022. https://www.analyticsvidhya.com/blog/2022/01/text-cleaning-methods-in-nlp/ (accessed Apr. 27, 2022).
W. Garbe, “1000x faster Spelling Correction. Sub-millisecond compound aware… | by Wolf Garbe | Towards Data Science,” 2017. https://towardsdatascience.com/symspellcompound-10ec8f467c9b (accessed Aug. 23, 2022).
A. Fardeen, “11 Techniques of Text Preprocessing Using NLTK in Python - MLK - Machine Learning Knowledge,” 2021. https://machinelearningknowledge.ai/11-techniques-of-text-preprocessing-using-nltk-in-python/ (accessed May 21, 2022).
K. Ganesan, “All you need to know about text preprocessing for NLP and Machine Learning - KDnuggets,” 2019. https://www.kdnuggets.com/2019/04/text-preprocessing-nlp-machine-learning.html (accessed Apr. 27, 2022).
S. Chakravarthy, “Tokenization for Natural Language Processing | by Srinivas Chakravarthy | Towards Data Science,” 2020. https://towardsdatascience.com/tokenization-for-natural-language-processing-a179a891bad4 (accessed Jul. 24, 2022).
R. Fauzi Rahmadzani, “Cara Kerja Word Embedding Word2Vec | Catatan Penelitian #5,” 2020. https://rifqifai.com/cara-kerja-word-embedding-word2vec/ (accessed May 05, 2022).
B. Ajose-Ismail, … O. A.-I., and undefined 2020, “Performance Analysis of Different Word Embedding Models for Text Classification,” Eprints.Federalpolyilaro.Edu.Ng, vol. 3, no. 6, pp. 1016–1020, 2020, [Online]. Available: http://eprints.federalpolyilaro.edu.ng/1650/.
S. Tazzyman, “Neural Network models | NLP-guidance.” https://moj-analytical-services.github.io/NLP-guidance/NNmodels.html (accessed May 24, 2022).
W. Widayat, “Analisis Sentimen Movie Review menggunakan Word2Vec dan metode LSTM Deep Learning,” J. Media Inform. Budidarma, vol. 5, no. 3, p. 1018, 2021, doi: 10.30865/mib.v5i3.3111.
M. Tauberg, “How Smart is Your News Source?. Text Data Analysis of 21 Different News… | by Michael Tauberg | Towards Data Science,” 2019. https://towardsdatascience.com/how-smart-is-your-news-source-1fe0c550c7d9 (accessed May 24, 2022).
J. Brownlee, “How to Choose Loss Functions When Training Deep Learning Neural Networks,” 2019. https://machinelearningmastery.com/how-to-choose-loss-functions-when-training-deep-learning-neural-networks/ (accessed Jul. 03, 2022).
O. Alharbi, “A Deep Learning Approach Combining CNN and Bi-LSTM with SVM Classifier for Arabic Sentiment Analysis,” Int. J. Adv. Comput. Sci. Appl., vol. 12, no. 6, pp. 165–172, 2021, doi: 10.14569/IJACSA.2021.0120618.
Downloads
Published
Issue
Section
License
The Authors submitting a manuscript do so on the understanding that if accepted for publication, copyright of the article shall be assigned to CoreIT journal and published by Informatics Engineering Department Universitas Islam Negeri Sultan Syarif Kasim Riau as publisher of the journal.
Authors who publish with this journal agree to the following terms:
Authors automatically transfer the copyright to the journal and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution-ShareAlike (CC BY SA) that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
Authors are able to enter into separate permission for 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 acknowledgement 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 (See The Effect of Open Access).
