SENTIMENT ANALYSIS OF CYBERBULLYING USING BIDIRECTIONAL LONG SHORT TERM MEMORY ALGORITHM ON TWITTER

Anisa Ika Safitri; Theopilus  Bayu Sasongko

doi:10.52436/1.jutif.2024.5.2.1922

Anisa Ika Safitri Informatics, Faculty of Computer Science, Universitas Amikom Yogyakarta, Indonesia
Theopilus Bayu Sasongko Informatics, Faculty of Computer Science, Universitas Amikom Yogyakarta, Indonesia

DOI: https://doi.org/10.52436/1.jutif.2024.5.2.1922

Keywords: bilstm, cyberbullying, sentiment analysis, twitter, word2vec

Abstract

Cyberbullying on social media such as Twitter is becoming an increasing social problem in today's society. Cyberbullying has a negative influence on mental health, increasing the risk of anxiety, sadness, and even suicide. The purpose of this research is to develop a model to classify tweets that contain or do not contain cyberbullying by applying the BiLSTM technique to sentiment analysis on Twitter. In this research, Word2Vec is used to weight each word in a tweet. The initial stage in this research is data collection with a total dataset of 47,692 tweets generated by Kaggle, preprocessing which consists of data cleaning, removing duplicates, case folding, tokenizing, stopword removal and lemmatization, classification and evaluation. This research uses the Bidirectional Long Short-Term Memory (Bi-LSTM) method and identifies patterns associated with bullying on social media. Testing uses Confusion Matrix and the results on classification show accuracy of 82.29%, precision of 82,04%, recall of 81,95% and F1-Score 81,89%. This sentiment analysis technique is expected to be the first step to combat and avoid cyberbullying on the Twitter platform. From several tests of existing reference algorithms, the classification accuracy performed includes having good performance.

Downloads

Download data is not yet available.

References

N. P. V. D. Saraswati, N. Yudistira, dan P. P. Adikara “Analisis Sentimen terhadap Perundungan Siber pada Twitter menggunakan Algoritma Bidirectional Encoder Representations from Transformer (BERT),” Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer, vol. 7, no 2, 909-916, Feb 2023.

E. A. A. Zahra, Y. Sibaroni, dan S. S. Prasetyowati, “Classification of Multi-Label of Hate Speech on Twitter Indonesia using LSTM and BiLSTM Method,” vol.4 no 2, 170-178. 2023.

D. Darwis, N. Siskawati, dan Z. Abidin, “PENERAPAN ALGORITMA NAIVE BAYES UNTUK ANALISIS SENTIMEN REVIEW DATA TWITTER BMKG NASIONAL,” J. Tekno Kompak, vol. 15, no. 1, hlm. 131, Feb 2021, doi: 10.33365/jtk.v15i1.744.

E. Subowo, F. A. Artanto, I. Putri, dan W. Umaedi, “BLTSM untuk analisis sentimen berbasis aspek pada aplikasi belanja online dengan cicilan,” Jurnal Fasilkom,vol 7, no. 2, Agu 2022.

A. Radjavani dan T. Bayu Sasongko, “Analisa Perbandingan Algoritma CNN dan LSTM untuk Klasifikasi Pesan Cyberbullying pada Twitter,” Indones. J. Comput. Sci., vol. 12, no. 4, Agu 2023, doi: 10.33022/ijcs.v12i4.3287.

M. Ridwan dan A. Muzakir, “HATE SPEECH CLASSIFICATION MODEL ON TWITTER DATA USING CNN-LSTM,” TEKNOMATIKA, Vol.12, No.02, September 2022 P-ISSN : 2087-9571, E-ISSN : 2541-335X IJCCS, Vol

V. B. Lestari dan E, U, Hanafi, “Lestari and Utami - Combining Bi-LSTM And Word2vec Embedding For Senti.” Vol. 13, No. 1, Ed. 2024

J. A. Pakpahan, Y. C. Panjaitan, J. Amalia, dan M. B. Pakpahan, “Model Klasifikasi Berita Palsu Menggunakan Bidirectional LSTM dan Word2vec sebagai Vektorisasi,” JATISI J. Tek. Inform. Dan Sist. Inf., vol. 9, no. 4, hlm. 3319–3331, Des 2022, doi: 10.35957/jatisi.v9i4.1332.

A. Muzakir dan U. Suriani, “Model Deteksi Berita Palsu Menggunakan Pendekatan Bidirectional Long Short-Term Memory (BiLSTM),” vol. 4, no. 2, 2023.

R. Z. Insani, C. Setianingsih, dan T. W. Purboyo, “Analisis Sentimen Komentar Berdasarkan Geo Tagged Menggunakan Algoritma Bilstm,” Vol.10, No.1 Februari 2023 |

S. Mutmainah, D. H. Fudholi, dan S. Hidayat, “Analisis Sentimen dan Pemodelan Topik Aplikasi Telemedicine Pada Google Play Menggunakan BiLSTM dan LDA,” vol. 7, 2023.

A. P. Hesaputra dan D. H. Fudholi, “Klasifikasi Pelanggaran Undang-Undang ITE pada Twitter Menggunakan LSTM dan BiLSTM”.

M. R. F. Kamarula dan N. Rochmawati, “Perbandingan CNN dan Bi-LSTM pada Analisis Sentimen dan Emosi Masyarakat Indonesia Di Media Sosial Twitter Selama Pandemik Covid-19 yang Menggunakan Metode Word2vec,” J. Inform. Comput. Sci. JINACS, hlm. 219–228, Nov 2022, doi: 10.26740/jinacs.v4n02.p219-228.

“Analisis Sentimen Opini Publik Menggunakan Metode BiLSTM Pada Media Sosial Twitter,” semiotika, Vol.2, No. 1, (2023)

R. W. Pratiwi, Y. Sari, dan Y. Suyanto, “Attention-Based BiLSTM for Negation Handling in Sentimen Analysis,” IJCCS Indones. J. Comput. Cybern. Syst., vol. 14, no. 4, hlm. 397, Okt 2020, doi: 10.22146/ijccs.60733.