This paper compares PyCaret AutoML and a CNN-BiLSTM model for detecting hate speech on Indonesian Twitter. The CNN-BiLSTM model achieved superior performance, with an accuracy of 83.8% and an F1-score of 81.2%, outperforming the best conventional model from PyCaret, Random Forest, which reached 77.2% accuracy and 77.0% F1-score. The study highlights that while PyCaret is effective for conventional benchmarking, the neural network approach is better suited for this specific task due to its ability to capture nuanced linguistic patterns. AI
Summary written by gemini-2.5-flash-lite from 2 sources. How we write summaries →
IMPACT Demonstrates the effectiveness of neural networks over conventional methods for nuanced text classification tasks.
RANK_REASON Academic paper comparing machine learning models for a specific task.