Year: 2025
Type: article
Abstract: This paper presents a deep learning approach for toxic comment classification using Bidirectional LSTM (Bi LSTM) in TensorFlow. The model identifies multiple categories of toxicity, including toxic, severe toxic, obscene, threat, insult, and identity hate. The dataset from Kaggle's Toxic Comment Classification Challenge is used for training and evaluation. Text vectorization is performed using both TF- IDF and TensorFlow's Text Vectorization layer. The system demonstrates efficient detection of toxic language, offering potential for real-time content moderation
Authors: Saqlain Ahmed, Prof. Parimal Kumar K R
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: diamond
OpenAlex ID: W4416502114