FINE-TUNING BIDIRECTIONAL ENCODER REPRESENTATIONS FROM TRANSFORMERS UNTUK MENDETEKSI BERITA PALSU

• AMSAL PARDAMEAN
• 14002309

---

ABSTRAK

ABSTRAK

 

 

Nama                   :    Amsal Pardamean

NIM                    :    14002309

Program Studi     :    Magister Ilmu Komputer

Jenjang                :    Strata Dua (S2)

Konsentrasi         :    Data Mining

Judul                    :    “Fine-Tuning Bidirectional Encoder Representations from Transformers untuk Mendeteksi Berita Palsu”

 

Berita palsu merupakan masalah utama dalam penyebaran berita saat ini. Dengan tidak dibatasi waktu dan tempat, penyebaran yang luas menjadi salah satu keunggulan media online. Berita palsu adalah informasi yang tidak benar, informasi yang direkayasa untuk menutupi informasi yang sebenarnya, tidak memiliki dasar faktual yang dibuat dalam bentuk berita yang memiliki daya tarik massal dan disajikan dalam kedok berita yang bernuansa asli dan sah untuk menipu atau berubah pikiran pembaca. Membedakan fake news dengan real news dapat dilakukan dengan salah satu cabang dari Artificial Intelligence yaitu Natural Language Processing yang berfokus pada pengolahan natural language atau bahasa manusia untuk berkomunikasi dengan model yang diusulkan yaitu Bidirectional Encoder Representations from Transformers (BERT) dan aplikasinya. dari Fine-Tuning. Hasil uji BERT Fine-Tunning didapatkan Performance Measure berupa akurasi 99.23%, Recall 99.46%, Precision 98.86%, dan F-Score 99.15% dan sebagai pembanding menggunakan model NBSVM dengan hasil Performance Measure pada bentuk akurasi 95.00%, Recall 95.00%, Presisi 95.00%, dan F-Score 95.00%. Model BERT Fine-Tunning mendapatkan hasil yang lebih baik pada setiap nilai Performance Measure setelah dilakukan pengujian pada lebih banyak detektor berita palsu daripada model NBSVM.

 

Kata kunci: Berita Palsu, Natural Language Processing, BERT, Fine-Tunning.

KATA KUNCI

Data Mining

---

DAFTAR PUSTAKA

DAFTAR PUSTAKA

 

Abdullah-All-Tanvir, Ehesas Mia Mahir, Saima Akhter, and Mohammad Rezwanul Huq. 2019. “Detecting Fake News Using Machine Learning and Deep Learning Algorithms.” 2019 7th International Conference on Smart Computing and Communications, ICSCC 2019: 1–5.

Annamoradnejad, Issa, Mohammadamin Fazli, and Jafar Habibi. 2020. “Predicting Subjective Features from Questions on QA Websites Using BERT.” arXiv: 240–44.

Cai, Ren et al. 2020. “Sentiment Analysis About Investors and Consumers in Energy Market Based on BERT-BiLSTM.” IEEE Access 8: 171408–15.

Crisanadenta Wintang Kencana, Erwin Budi Setiawan, and Isman Kurniawan, “Hoax Detection System on Twitter using Feed-Forward and Back-Propagation Neural Networks Classification Method”, RESTI, vol. 4, no. 4, pp. 655 - 663, Aug. 2020.

Devlin, Jacob, Ming Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. “BERT: Pre-Training of Deep Bidirectional Transformers for Language Understanding.” NAACL HLT 2019 - 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies - Proceedings of the Conference 1(Mlm): 4171–86.

Dong, Junchao, Feijuan He, Yunchuan Guo, and Huibing Zhang. 2020. “A Commodity Review Sentiment Analysis Based on BERT-CNN Model.” 2020 5th International Conference on Computer and Communication Systems, ICCCS 2020: 143–47.

D’Sa, Ashwin Geet, Irina Illina, and Dominique Fohr. 2020. “BERT and FastText Embeddings for Automatic Detection of Toxic Speech.” Proceedings of 2020 International Multi-Conference on: Organization of Knowledge and Advanced Technologies, OCTA 2020.

Fronzetti Colladon, Andrea. 2020. “Forecasting Election Results by Studying Brand Importance in Online News.” International Journal of Forecasting 36(2): 414–27. https://doi.org/10.1016/j.ijforecast.2019.05.013.

F. Demirk?ran, A. Çay?r, U. Ünal and H. Da?, "Website Category Classification Using Fine-tuned BERT Language Model," 2020 5th International Conference on Computer Science and Engineering (UBMK), Diyarbakir, Turkey, 2020, pp. 333-336, doi: 10.1109/UBMK50275.2020.9219384.

Gao, Zhengjie, Ao Feng, Xinyu Song, and Xi Wu. 2019. “Target-Dependent Sentiment Classification with BERT.” IEEE Access 7: 154290–99.

Gilda, Shlok. 2018. “Evaluating Machine Learning Algorithms for Fake News Detection.” IEEE Student Conference on Research and Development: Inspiring Technology for Humanity, SCOReD 2017 - Proceedings 2018-Janua: 110–15.

Han, Wenlin, and Varshil Mehta. 2019. “Fake News Detection in Social Networks Using Machine Learning and Deep Learning: Performance Evaluation.” Proceedings - IEEE International Conference on Industrial Internet Cloud, ICII 2019 (Icii): 375–80.

Https://www.kaggle.com/anthonyc1/fake-news-classifier-final-project.

Li, Wenting et al. 2019. “The Automatic Text Classification Method Based on Bert and Feature Union.” Proceedings of the International Conference on Parallel and Distributed Systems - ICPADS 2019-Decem: 774–77.

Lin, Chuan Jie, Chao Hsiang Huang, and Chia Hao Wu. 2019. “Using BERT to Process Chinese Ellipsis and Coreference in Clinic Dialogues.” Proceedings - 2019 IEEE 20th International Conference on Information Reuse and Integration for Data Science, IRI 2019: 414–18.

Liu, Songsong, Haijun Tao, and Shiling Feng. 2019. “Text Classification Research Based on Bert Model and Bayesian Network.” Proceedings - 2019 Chinese Automation Congress, CAC 2019: 5842–46.

Ly, Antoine, Benno Uthayasooriyar, and Tingting Wang. 2020. “A Survey on Natural Language Processing (Nlp) and Applications in Insurance.” : 1–34. http://arxiv.org/abs/2010.00462.

Maharani, Warih. 2020. “Sentiment Analysis during Jakarta Flood for Emergency Responses and Situational Awareness in Disaster Management Using BERT.” 2020 8th International Conference on Information and Communication Technology, ICoICT 2020.

Munikar, Manish, Sushil Shakya, and Aakash Shrestha. 2019. “Fine-Grained Sentiment Classification Using BERT.” arXiv 1: 1–5.

Rusli, Andre, Julio Christian Young, and Ni Made Satvika Iswari. 2020. “Identifying Fake News in Indonesian via Supervised Binary Text Classification.” Proceedings - 2020 IEEE International Conference on Industry 4.0, Artificial Intelligence, and Communications Technology, IAICT 2020: 86–90.

Sistem, Rekayasa. 2021. “JURNAL RESTI Hoax Detection on Twitter Using Feed-Forward and Back-Propagation.” 1(10): 655–63.

Smitha, N. 2020. “Performance Comparison of Machine Learning Classifiers for Fake News Detection.” : 696–700.

Solheim Bojer, Casper, and Jens Peder Meldgaard. 2020. “Learnings from Kaggle’s Forecasting Competitions.” (February): 1–24. https://www.kaggle.com/.

Sutoyo, Edi, and Ahmad Almaarif. 2020. “Educational Data Mining Untuk Prediksi Kelulusan Mahasiswa Menggunakan Algoritme Naïve Bayes Classifier.” Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) 4(1): 95–101.

Wang, Tianyi, Ke Lu, Kam Pui Chow, and Qing Zhu. 2020. “COVID-19 Sensing: Negative Sentiment Analysis on Social Media in China via BERT Model.” IEEE Access 8: 138162–69.

Xue, Kui et al. 2019. “Fine-Tuning BERT for Joint Entity and Relation Extraction in Chinese Medical Text.” arXiv: 892–97.

Yadav, Jaideep, Devesh Kumar, and Dheeraj Chauhan. 2020. “Cyberbullying Detection Using Pre-Trained BERT Model.” Proceedings of the International Conference on Electronics and Sustainable Communication Systems, ICESC 2020 (Icesc): 1096–1100.

Zhang, Xichen, and Ali A. Ghorbani. 2020. “An Overview of Online Fake News: Characterization, Detection, and Discussion.” Information Processing and Management 57(2): 102025. https://doi.org/10.1016/j.ipm.2019.03.004.

Zhao, Liping et al. 2020. “Natural Language Processing (NLP) for Requirements Engineering: A Systematic Mapping Study.” arXiv (v).