A Hybrid TF-IDF and RNN Model for Multi-label Classification of the Deep and Dark Web

The classification of content on the deep and dark web has been a topic interest for researchers. Researchers focus adopting more efficient effective methods as data available platforms continues to grow. Multi-label is approach simultaneously categorizing into multiple classes. To address this, hybrid combining Term Frequency-Inverse Document Frequency (TF-IDF) Recurrent Neural Network (RNN) proposed. involves preprocessing dataset Hypertext Markup Language (HTML) documents, selecting specific HTML tags generate embeddings using TF-IDF, an RNN model multi-label classification. proposed was evaluated against commonly used (Binary Relevance, Classifier Chains, Label Powerset) precision, recall, F1-score evaluation metrics, demonstrating promising results in accurately classifying from web. This contribution represents noteworthy advancement researchers analysts working this field.