ksethi/Toxic-Comment-Classification

Model Card for Model ID

This model was built to classify various forms of toxic comments in online discussions. It is a multi-headed model capable of detecting different types of toxicity such as threats, obscenity, insults, and identity-based hate. The model is based on the Toxic Comment Classification Challenge (2018) and fine-tuned using BERT.

Model Details

Model Description

base_model: "google-bert/bert-base-uncased" architecture: "BERT (Bidirectional Encoder Representations from Transformers)" task: "Multi-label text classification" pipeline_tag: "text-classification" license: "Apache-2.0" framework: "PyTorch"

Model Sources [optional]

• Repository: [More Information Needed]
• Paper [optional]: [More Information Needed]
• Demo [optional]: [More Information Needed]

Uses

- "Research purposes, especially in identifying and mitigating biases in automated text classification."
- "Content moderation, helping flag harmful or toxic content across online platforms faster."
- "Fine-tuning: The model can be further trained with more specific or updated datasets for improved generalization in real-world applications."

  supported_labels:
- "Toxic"
- "Severe Toxic"
- "Obscene"
- "Threat"
- "Insult"
- "Identity Hate"

Direct Use

Already tuned and ready for use

Out-of-Scope Use

None

Bias, Risks, and Limitations

  The model tends to classify comments containing profanity, swearing, or insults as toxic, 
  regardless of tone or intent (e.g., sarcasm or humor). This can introduce bias against groups 
  that might use such language in self-referential or comedic ways. 
  Additional fine-tuning on diverse datasets is recommended to address these biases and improve 
  the model’s fairness.
  

Recommendations

Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.

How to Get Started with the Model

Use the code below to get started with the model.

[More Information Needed]

Training Details

Training Data

The model was trained on the Toxic Comment Classification Challenge dataset, which consists of comments from Wikipedia that were labeled as toxic or non-toxic based on their content. The dataset includes various forms of toxic speech.

Training Procedure

Training Hyperparameters

• Training regime: [More Information Needed]

Evaluation

Testing Data, Factors & Metrics

Testing Data

[More Information Needed]

Factors

[More Information Needed]

Metrics

[More Information Needed]

Results

[More Information Needed]

Summary

Model Examination [optional]

[More Information Needed]

Environmental Impact

Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).

• Hardware Type: [More Information Needed]
• Hours used: [More Information Needed]
• Cloud Provider: [More Information Needed]
• Compute Region: [More Information Needed]
• Carbon Emitted: [More Information Needed]

Technical Specifications [optional]

Model Architecture and Objective

[More Information Needed]

Compute Infrastructure

[More Information Needed]

Hardware

[More Information Needed]

Software

[More Information Needed]

Citation [optional]

BibTeX:

[More Information Needed]

APA:

[More Information Needed]

Glossary [optional]

[More Information Needed]

More Information [optional]

[More Information Needed]

Model Card Authors [optional]

[More Information Needed]

Model Card Contact

[More Information Needed]