Claim Missing Document
Check
Articles

Found 2 Documents
Search
Journal : JITK (Jurnal Ilmu Pengetahuan dan Komputer)

MODEL OF INDONESIAN CYBERBULLYING TEXT DETECTION USING MODIFIED LONG SHORT-TERM MEMORY Mariana Purba; Paisal Paisal; Cahyo Pambudi Darmo; Handrie Noprisson; Vina Ayumi
JITK (Jurnal Ilmu Pengetahuan dan Teknologi Komputer) Vol. 10 No. 1 (2024): JITK Issue August 2024
Publisher : LPPM Nusa Mandiri

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33480/jitk.v10i1.5239

Abstract

Cyberbullying, in its essence, refers to the deliberate act of exploiting technological tools to inflict harm upon others. Typically, this offensive conduct is perpetuated repeatedly, as the perpetrator takes solace in concealing their true identity, thereby avoiding direct exposure to the victim's reactions. It is worth noting that the actions of the cyberbully and the responses of the individual being cyberbullied share an undeniable interconnection. The main objective of this study was to identify and analyze Instagram comments that contain bullying words using a model of WLSTML2 which is an optimization of a long short-term memory network with word-embedding and L2 regularization. This experiment using dataset with negative labels as many as 400 data and positive as many as 400 data. In this study, a comparison of 70% training data and 30% testing data was used. Based on experimental results, the WLSTMDR model obtained 100% accuracy at the training stage and 80% accuracy at the testing stage. The WLSTML2 model received an accuracy of 99.25% at the training stage and an accuracy of 83% at the testing stage. The WLSTML1 model obtained an accuracy of 97.01% at the training stage and an accuracy of 80% at the testing stage. Based on the experimental results, the WLSTML2 model gets the best accuracy at the training and testing stages. At the testing stage of 132 data, it was found that the positive label data predicted to be correct was 56 data and the negative label data that was predicted to be correct was 53 data.
MODEL OF CYBERBULLYING DETECTION ON SOCIAL MEDIA USING MULTI-LABEL DEEP LEARNING: A COMPARATIVE STUDY Lemi Iryani; Junaidi Junaidi; Paisal Paisal; Mariana Purba; Nia Umilizah; Bakhtiar Bakhtiar; Nur Ani
JITK (Jurnal Ilmu Pengetahuan dan Teknologi Komputer) Vol. 10 No. 4 (2025): JITK Issue May 2025
Publisher : LPPM Nusa Mandiri

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33480/jitk.v10i4.6004

Abstract

Cyberbullying is the deliberate act of using technology to harm others. This study aims to analyze 400 Instagram comments obtained via API from previous research. The data were labeled into three classes: negative (containing cyberbullying), positive (non-bullying, supportive), and neutral (neither positive nor negative). The data for experiment was divided into 70% for training and 30% for testing. The research methodology consists of three main stages. The first stage is text preprocessing, which includes tokenization (splitting comments into tokens), filtering (removing unimportant words or stop-words), and stemming (converting words with affixes into their root forms). The second stage is classification analysis using BiLSTM, LSTM, RNN, and CNN-1D methods. The third stage is evaluation by comparing the model's classification results with manually labeled data using accuracy as the evaluation metric. The results show that the BiLSTM model performed the best, achieving an accuracy of 98.51% on the training data and 81.82% on the testing data. The BiLSTM method used in this study can be further adapted to enhance the effectiveness of cyberbullying detection in various applications.
Co-Authors . Andriansjah Abdal, Abdal Abdul, Ikhsan Abdullah Fadily Adesia Destinirenza Adris Ade Putra Africano, Fernando Afrizawati Afrizawati Afrizawati Afrizawati Ahmad Zabidi Akhmad Taufik Akhmad Taufik Al Anshori, Muhammad Zakariya Alhanina, Shiva Amilizamiarti, Amilizamiarti Amrullah Amrullah Andi Irawan Apriyanti, Tria Ariawan Bayu Wicaksono Asrul Asrul Aya Yuriestia Arifin, Aya Yuriestia Ayumi, Vina Azhar Andika Putra Bainil Yulina Bakhtiar, Bakhtiar. BASTIAN, ALVIAN Beti Ernawati Dewi Beti Yanuri Posha Cahyo Pambudi Darmo Darmo, Cahyo Pambudi Darvianti Darvianti DEKA LARASATI Deni Irawan Dian Kurniasari Dicky Andiarsa Edi Yanto Eko Suhartono Elga Amira Rizky Erly Krisnanik Farhan Fathun Nur, Muh Fernando Firman Hamzah Habriansyah, Imran Hadi, Jauhari Hamidah . Hendra Marcos, Hendra Hendra Sastrawinata Hendra Sastrawinata Heni Pujiastuti Hery Nirwanto, Hery Hidayat Hidayat HR, Yuliani Ikbal Aziz Ikhwan, Muhammad Ikhwan Ali Imran Habriansyah Indah Agus Setiorini Indah Pratiwi Indah Pratiwi Intan Hesti Indriana Jumhur, Jalaluddin Junaidi Junaidi Kadir Muhammad, Abdul Kesuma, Lucky Indra KHOIRUN NISAK Lemi Iryani Leni Sabrina Lewi Lewi Liestiana Indriyati Lusiana Lusiana Lutfhi Fatah M Arief Rahman M. Yusuf Maghfiroh, Henik Magribi, La Ode Muh Manja Manja Mariana Purba Mariana Purba Maulana, M. Riska Mawazin, Fawaz Meilianti Meilianti Miarti, Amiliza Mohd. Winario Muhammad Rasyid Ridha Muhammad Zakir Muhemin, Muhemin Mukhtar Mukhtar Mukhtar Mukhtar mukhtar mukhtar Nabilah Angraini Naraloka, Therezia Nasrullah Nasrullah Nia Umilizah Noprisson, Handrie Nur Ani NURUL HIDAYAT Paramita, Vilia Darma Pariyati, Pariyati Primasari Primasari, Primasari Purba, Mariana Putri, Dhea Radika Reynalza Anggri Septi Ridho, Sari Lestari Zainal Rifqi Muhammad Riyanto Riyanto Sabari Sabari Sabli, Habsah Binti Mohammad Salamiah . Samhuddin Samhuddin, Samhuddin Sapriadi Sapriadi Sari, Ayu Jelita Setiorini, Indah Agus Siregar, Esron Mangatas Sodikin Sodikin Subarkah, Pungkas Sukasri, Arifah Tasya Tasya Tjahjani Mirawati Sudiro Tjambolang, Tjare Anugerah Triwahyu, Endang Walian, Anang Yeni Widiyawati Zamheri, Ahmad Zurohaina, Zurohaina