Implementasi Algoritma Long Short-Term Memory (LSTM) Untuk Mendeteksi Ujaran Kebencian (Hate Speech) Pada Kasus Pilpres 2019

Talita, Aini Suri; Wiguna, Aristiawan

doi:10.30812/matrik.v19i1.495

Cited by 7 publications

(3 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Paper [9] membahas mengenai algoritma Long Short-Term Memory (LSTM) untuk mendeteksi ujaran kebencian berkaitan dengan Pemilihan Presiden (Pilpres) 2019. Algoritma ini dilatih dengan menggunakan dataset yang bersumber dari media sosial Facebook.…”

Section: Pendahuluanunclassified

Deteksi Berita Palsu Menggunakan Algoritma Random Forest

Nurohanisah,

Astuti,

Muhammad Basysyar

2024

jati

View full text Add to dashboard Cite

Dalam era digital yang dipenuhi oleh penyebaran berita palsu atau yang lebih dikenal dengan istilah "hoaks," tantangan untuk memerangi penyebaran informasi yang salah dan menyesatkan semakin mendesak. Berita palsu memiliki potensi untuk merusak kepercayaan publik, menciptakan kebingungan, dan berdampak negatif pada masyarakat. Oleh karena itu, penelitian ini bertujuan untuk mengklasifikasi berita palsu yang menggunakan algoritma Random Forest, dengan tujuan mengeksplorasi cara menggunakan algoritma Random Forest dalam mengidentifikasi dan memisahkan berita palsu dari berita yang asli. Penelitian ini dilakukan dengan memanfaatkan dataset yang mencakup berbagai jenis berita, termasuk berita palsu dan berita asli, yang telah dianalisis dan dikategorikan oleh ahli faktual. Teknik pemrosesan bahasa alami (NLP) digunakan untuk mengekstraksi fitur-fitur penting dari teks berita. Penelitian ini menggunakan algoritma Random Forest untuk klasifikasi. Random Forest bekerja dengan cara menggabungkan sejumlah besar pohon keputusan yang independen untuk membuat keputusan akhir. Setiap pohon membuat prediksi, dan hasil akhirnya didasarkan pada mayoritas prediksi dari pohon-pohon tersebut. Kelebihan utama Random Forest adalah kemampuannya dalam mengatasi overfitting dan meningkatkan akurasi dengan menggabungkan prediksi dari beberapa model. Evaluasi dilakukan dengan menggunakan metrik akurasi, presisi, recall, dan F1-score. Hasil penelitian menunjukkan bahwa klasifikasi berita palsu menggunakan algoritma Random Forest mampu mengklasifikasikan berita dengan tingkat akurasi yang memuaskan. Hasil akhir menunjukkan bahwa sistem ini memiliki kinerja yang baik dalam membedakan berita palsu dari berita asli, dengan akurasi rata-rata di atas 87%.

show abstract

Section: Pendahuluanunclassified

Deteksi Berita Palsu Menggunakan Algoritma Random Forest

Nurohanisah,

Astuti,

Muhammad Basysyar

2024

jati

View full text Add to dashboard Cite

show abstract

“…Recurrent neural networks ( Paetzold, Zampieri & Malmasi, 2019 ) are a type of neural network in which the connections between nodes form a directed graph along a temporal sequence. Among the different variants of this type of network, the Long Short-Term Memory Network (LSTM) ( Talita & Wiguna, 2019 ; Bisht et al, 2020 ; Zhao et al, 2020 ; Zhang et al, 2021 ), which were specifically designed to avoid the problem of long-term dependency. As with CNNs, a correct extraction of text features prior to the learning period of the network, which is carried out by means of word embeddings, is of vital importance.…”

Section: Related Workmentioning

confidence: 99%

Detecting racism and xenophobia using deep learning models on Twitter data: CNN, LSTM and BERT

Benítez-Andrades

González-Jiménez

López-Brea

et al. 2022

PeerJ Computer Science

View full text Add to dashboard Cite

With the growth that social networks have experienced in recent years, it is entirely impossible to moderate content manually. Thanks to the different existing techniques in natural language processing, it is possible to generate predictive models that automatically classify texts into different categories. However, a weakness has been detected concerning the language used to train such models. This work aimed to develop a predictive model based on BERT, capable of detecting racist and xenophobic messages in tweets written in Spanish. A comparison was made with different Deep Learning models. A total of five predictive models were developed, two based on BERT and three using other deep learning techniques, CNN, LSTM and a model combining CNN + LSTM techniques. After exhaustively analyzing the results obtained by the different models, it was found that the one that got the best metrics was BETO, a BERT-based model trained only with texts written in Spanish. The results of our study show that the BETO model achieves a precision of 85.22% compared to the 82.00% precision of the mBERT model. The rest of the models obtained between 79.34% and 80.48% precision. On this basis, it has been possible to justify the vital importance of developing native transfer learning models for solving Natural Language Processing (NLP) problems in Spanish. Our main contribution is the achievement of promising results in the field of racism and hate speech in Spanish by applying different deep learning techniques.

show abstract

“…Peneliti [10] melakukan penelitian pada objek hate speech atau ujaran kebecian. Pada penelitian ini menggunakan metode Long Shor-Term Memory (LSTM) akan diimplementasikan untuk mendeteksi ujaran kebencian (hate speech) berkaitan dengan Pemilihan Presiden (Pilpres) 2019 .…”

Section: Pendahuluanunclassified

Klasifikasi Nama Paket Pengadaan Menggunakan Long Short-Term Memory (LSTM) Pada Data Pengadaan

Fajri¹,

Syaiful²

2022

bits

View full text Add to dashboard Cite

Every year the government always holds procurement of goods and services (tenders) which are informed through the Electronic Procurement Service (LPSE) or the General Procurement Plan Information System (SIRUP). The process of selecting the type of procurement is still manual, namely by selecting the package category so that it is possible for mistakes to occur such as the type of service procurement into the category of goods procurement type or vice versa. Therefore, this research proposes to use the Natural Language Processing (NLP) method that can classify these packages based on existing categories. The method used is Long Short-Term Memory (LSTM) by comparing existing classification methods such as naïve bayes, logistic regression, decision tree, XG Boost, Gradient Boost, Random Forest and Support Vector Machine. The results obtained by the LSTM method have a higher accuracy than other methods, with an accuracy of 90.25%. With a parameter configuration of 100 units in the LSTM layer, epoch 10, batch size 64 and validation step 5

show abstract

Implementasi Algoritma Long Short-Term Memory (LSTM) Untuk Mendeteksi Ujaran Kebencian (Hate Speech) Pada Kasus Pilpres 2019

Cited by 7 publications

References 0 publications

Deteksi Berita Palsu Menggunakan Algoritma Random Forest

Deteksi Berita Palsu Menggunakan Algoritma Random Forest

Detecting racism and xenophobia using deep learning models on Twitter data: CNN, LSTM and BERT

Klasifikasi Nama Paket Pengadaan Menggunakan Long Short-Term Memory (LSTM) Pada Data Pengadaan

Contact Info

Product

Resources

About