This study investigates enhancing multi-label hate speech and abusive language detection on Indonesian Twitter using Recurrent Neural Networks (RNNs) with hyperparameter tuning. A dataset of Indonesian tweets labeled for various hate speech and abusive language categories was preprocessed through text cleaning, tokenization, and sequence padding. A baseline RNN model was initially constructed and evaluated. Hyperparameter tuning was then performed using Keras Tuner to optimize performance. The best hyperparameters identified were an embedding dimension of 32, 32 LSTM units, and a dropout rate of 0.2. The tuned model was trained and compared with the baseline. Results indicated improved precision for labels like Abusive, HS_Group, HS_Moderate, and HS_Strong, but a decline in recall and F1-scores for labels like HS_Religion and HS_Race. Overall performance metrics showed a slight decline, highlighting trade-offs in the tuning process. In conclusion, while hyperparameter tuning can enhance certain performance aspects, it also introduces complexities and trade-offs. It is recommended to use hyperparameter tuning in model optimization with careful consideration of application requirements. Further research will explore different model architectures and additional tuning strategies for better overall performance.
