This research paper compares automated machine learning (AutoML) and Bidirectional Long Short-Term Memory (BiLSTM) models for detecting cyberbullying in Indonesian Instagram comments. The study utilized a dataset of 650 comments, evaluating various machine learning algorithms like Logistic Regression and deep learning models including BiLSTM with Attention. Results indicated that Logistic Regression was the top performer among traditional machine learning methods, while BiLSTM with Attention showed the best deep learning performance, underscoring the importance of tailored preprocessing for informal Indonesian text. AI
IMPACT Provides insights into effective NLP techniques for informal language, potentially aiding social media platforms in content moderation.
RANK_REASON Academic paper comparing machine learning and deep learning models for a specific NLP task.
- AutoML
- Bahdanau Attention
- BiLSTM
- Logistic Regression
- Martin Clinton Tosima Manullang
- Naive Bayes
- Support Vector Machine
- TF-IDF
AI-generated summary · Google Gemini · from 2 sources. How we write summaries →
