Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
September 5, 2025

Toxic language detection on social media: a critical linguistic approach to online hate speech

View Full Paper
Ask AI
Bookmark
Share

Authors

AKArie Purwa KusumaNRNurina Kurniasari Rahmawati

Discussion

Loading...

Member takes

Overview

This study integrates machine learning and Critical Discourse Analysis to improve toxic language detection, indicating a need for fairer content moderation systems.

Key Points

  • The analysis found that 25.67% of 15,000 posts contained toxic language, highlighting the prevalence of hate speech on social media.
  • Critical Discourse Analysis revealed hidden expressions of hate speech through irony and metaphor, challenging the effectiveness of automated tools.
  • The study employed machine learning techniques, specifically a BERT-based model, to classify posts for toxic language detection.
  • The findings call for improved contextual approaches in content moderation systems to combat online hate speech effectively.

Cite This Study

Kusuma et al. (2025) studied this question.

synapsesocial.com/papers/68bb46a86d6d5674bccfe2efhttps://doi.org/10.64268/jllm.v1i01.4
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. 1Intelligent Toxic Comment Detection Using Machine Learning And Natural Language Processing Techniques2026
  2. 2Intelligent Toxic Comment Detection Using Machine Learning And Natural Language Processing Techniques2026
  3. 3Advanced Social Media Toxic Comments Detection System Using AI2024
  4. 4Harnessing Machine Learning to Unveil Emotional Responses to Hateful Content on Social Media2024 · 2 citations
  5. 5Taming The Hate: Machine Learning Analysis Of Hate Speech2024 · 4 citations