Sistem Pendeteksi Kalimat Umpatan Di Media Sosial Dengan Model Neural Network

Sahrul, Sahrul; Rahman, Ahmad Fauzan; Normansyah, Muhammad Dzaky; Irawan, Ade

doi:10.24912/computatio.v3i2.6032

Cited by 4 publications

(5 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Beberapa hasil penelitian dilakukan oleh beberapa peneliti untuk membuktikan kutukan tersebut. Metode yang umum termasuk naive bay, mesin vektor pendukung, metode semantik, dan metode obfuscation, yang semuanya memperhitungkan konteks kalimat atau frasa yang tidak dipahami dengan baik oleh komputer (Sahrul et al, 2019). Kelebihannya adalah dapat mendeteksi konten negatif yang biasanya muncul dengan kalimat umpatan dalam sistem ini dapat mendeteksi tidak hanya kata-per-kata.…”

Section: Hasil Penelitian Dan Pembahasanunclassified

See 1 more Smart Citation

Teknologi Informasi Efektif Mendeteksi Cyberbullying

Sarwani¹,

Sianturi²,

Kustianti³

et al. 2022

J-HESTECH (Journal Heal. Educ. Sci. Technol.

View full text Add to dashboard Cite

Pengguna media sosial berisiko mengalami gangguan kesehatan mental. Masalah kesehatan mental dapat terjadi dengan cyberbullying. Cyberbullying yang terjadi di media sosial berupa komentar kasar, ancaman, hinaan, fitnah bahkan pelecehan yang diberikan oleh netizen. Cyberbullying dapat menggoyahkan kondisi kesehatan mental seseorang bahkan berdampak pada bunuh diri. Cyberbullying akan sangat merugikan baik secara mental maupun produktif. Cyberbullying harus dideteksi sejak dini untuk mencegah dampak buruk bagi pengguna media sosial. Dengan kemajuan teknologi, dapat digunakan untuk mendeteksi cyberbullying yang terjadi di media sosial. Artikel ini menggunakan pendekatan metode literature review yaitu narrative literature review 10 artikel pemanfaatan teknologi pendeteksi cyberbullying periode 2011 – 2021 dengan tujuan untuk mengetahui komentar cyberbullying pada akun/postingan seseorang. Oleh karena itu, deteksi cyberbullying mencoba mengumpulkan dataset global di media sosial (Facebook, Instagram, Twitter, dll), dengan mengklasifikasikan metode Machine Learning. Setiap metode algoritma dievaluasi menggunakan akurasi, presisi, recall, dan skor F1 untuk menentukan kinerja tingkat klasifikasi Keywords:Cyberbullying, Media Sosial, Gangguan Kesehatan Mental Social media users are at risk for mental health disorders. Mental health problems can occur with cyberbullying. Cyberbullying that occurs on social media is in the form of rude comments, threats, insults, slander and even harassment given by netizens. Cyberbullying can destabilize a person's mental health condition and even lead to suicide. Cyberbullying will be very detrimental both mentally and productively. Cyberbullying must be detected early to prevent adverse effects on social media users. With advances in technology, it can be used to detect cyberbullying that occurs on social media. This article uses a literature review method approach, namely a narrative literature review of 10 articles on the use of cyberbullying detection technology for the period 2011 – 2021 with the aim of finding out cyberbullying comments on someone's account/post. Therefore, cyberbullying detection tries to collect global datasets on social media (Facebook, Instagram, Twitter, etc.), by classifying Machine Learning methods. Each algorithm method is evaluated using accuracy, precision, recall, and F1 scores to determine the classification level performance Keywords: Cyberbullying, Social Media, Mental Health Disorders

show abstract

Section: Hasil Penelitian Dan Pembahasanunclassified

“…Kekurangan: Lamanya proses pelatihan. Menggunakan data dalam jumlah besar dapat memakan waktu yang sangat lama (Sahrul et al, 2019).…”

Section: Hasil Penelitian Dan Pembahasanunclassified

Teknologi Informasi Efektif Mendeteksi Cyberbullying

Sarwani¹,

Sianturi²,

Kustianti³

et al. 2022

J-HESTECH (Journal Heal. Educ. Sci. Technol.

View full text Add to dashboard Cite

show abstract

“…Researchers also classify Twitter datasets into two labels: offensive (label 1) and not offensive (label 2). Researchers perform the synthetic minority oversampling technique (SMOTE) because the amount of data between labels one and two is not balanced [15] Social media applications, especially Twitter, are a personal means to express opinions, their hearts, and so on. Twitter is also used by various organizations, agencies, and individuals.…”

Section: Introductionmentioning

confidence: 99%

Sentiment Analysis of Hate Speech on Twitter Public Figures with AdaBoost and XGBoost Methods

Suhendra

Jondri

Indwiarti

2022

mib

View full text Add to dashboard Cite

Public figures are often scrutinized by social media users, either because of what they say or even because of their role in a television series. Generally, public figures upload something on their social media accounts to help shape their image. But not everyone who sees it is happy. Some even dislike the upload. This study aims to determine public sentiment towards public figure Anya Geraldine conveyed on Twitter in Indonesian. The classification process in this study uses the Adaptive Boosting (AdaBoost) and Extreme Gradient Boosting (XGBoost) classification methods with text preprocessing using cleaning, case folding, tokenization, and filtering. The data used are tweets in Indonesian with the keyword ”@anyaselalubenar”, with a total dataset of 7,475 tweets divided into 6,887 positive and 588 negative tweets. From the label results using oversampling to avoid excessive overfitting problems. The feature used is TF-IDF weighting. Four experimental scenarios were carried out to validate the effectiveness of the model used: first model performance without oversampling, second model performance with oversampling, third model performance with undersampling, and fourth model performance with Hyperparameter tune. The experimental results show that XGBoost+SMOTE+Hyperparameter achieved 95% compared to AdaBoost+SMOTE+Hyperparameter of 87%. The application of SMOTE and Hyperparameter tune is proven to overcome the problem of data imbalance and get better classification results.

show abstract

“…Penelitian (Maya, 2015) tidak dipahami dengan baik oleh komputer (Sahrul et al, 2019). Kelebihannya yitu dapat mendeteksi konten negatif yang biasanya muncul dengan kalimat umpatan, dalam sistem ini dapat mendeteksi tidak hanya kata-per-kata.…”

unclassified

“…Kekurangannya yaitu lamanya proses pelatihan. Menggunakan data dalam jumlah besar dapat memakan waktu yang sangat lama (Sahrul et al, 2019).…”

unclassified

Teknologi Informasi Efektif Mendeteksi Cyberbullying

Sarwani

2022

JoB

View full text Add to dashboard Cite

Social media users are at risk for mental health disorders. Mental health problems can occur with cyberbullying. Cyberbullying that occurs on social media is in the form of rude comments, threats, insults, slander and even harassment given by netizens. Cyberbullying can shake a person's mental health condition and even have an impact on suicide. Cyberbullying will be very detrimental both mentally and productively. Cyberbullying must be detected early to prevent adverse effects on social media users. With advances in technology, it can be used to detect cyberbullying that occurs on social media. This article uses a literature review method approach, namely narrative literature review of 10 articles on the use of technology for cyberbullying detection in the period 2011 - 2021 with the aim of finding out cyberbullying comments on someone's account/post. Therefore, cyberbullying detection tries to collect global datasets on social media (Facebook, Instagram, Twitter, etc.), by classifying the Machine Learning method. Each algorithm method is evaluated using accuracy, precision, recall, and F1 score to determine the performance of the classification level

show abstract

Sistem Pendeteksi Kalimat Umpatan Di Media Sosial Dengan Model Neural Network

Cited by 4 publications

References 0 publications

Teknologi Informasi Efektif Mendeteksi Cyberbullying

Teknologi Informasi Efektif Mendeteksi Cyberbullying

Sentiment Analysis of Hate Speech on Twitter Public Figures with AdaBoost and XGBoost Methods

Teknologi Informasi Efektif Mendeteksi Cyberbullying

Contact Info

Product

Resources

About