Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
October 13, 2025International Scientific Journal of Engineering and Management

Toxic Comment Detection Using Machine Learning

View Full Paper
Ask AI
Bookmark
Share

Authors

KSK. SuthaPNP. Nandhini

Discussion

Loading...

Member takes

Overview

This research demonstrates the effectiveness of deep learning models, including BiLSTM and BERT, for classifying toxic comments across various types of toxicity.

Key Points

  • Deep learning models achieve superior performance in detecting toxic comments compared to traditional methods.
  • BiLSTM and BERT models classify multiple types of toxicity, including threats and insults, with high accuracy.
  • Extensive text preprocessing and advanced word embeddings were employed to enhance model effectiveness.
  • The study tested these models on large-scale datasets, such as the Jigsaw Toxic Comment Classification Challenge.

Cite This Study

Sutha et al. (2025) studied this question.

synapsesocial.com/papers/68ed1896f29694dd1da78d72https://doi.org/10.55041/isjem05097
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1An Integrated Model for Social Media Toxic Comments Detection: Fusion of High-Dimensional Neural Network Representations and Multiple Traditional Machine Learning Algorithms2022
  2. 2Advanced Toxic Comment Classification Using Multi-‎Architecture Generative AI Techniques2025
  3. 3Feature Engineering in the Transformer Era: A Controlled Study on Toxic Comment Classification2025
  4. 4Multilingual Toxic comments Classification using Bert2025
  5. 5Sentiment Analysis of Twitter Comments Based on Deep Learning2025